Search

This is the supplementary material for the research paper Exploring Explainability: A Definition, a Model, and a Knowledge Catalogue accepted at the IEEE 29th Requirements Engineering Conference. In particular, more details on the Systematic Literature Review (SLR) – e.g., inclusion/exclusion criteria, complete list of analyzed papers, codes, etc. – and our workshops can be found here.

Background Discussing patient preferences for cardio‐pulmonary resuscitation (CPR) is routine in hospital admission for older people. The way the conversation is conducted plays an important role for patient comprehension and the ethics of decision making. Objective The objective was to examine how CPR is explained in geriatric rehabilitation hospital admission interviews, focussing on circumstances in which physicians explain CPR and the content of these explanations. Method We recorded forty‐three physician‐patient admission interviews taking place in a hospital in French‐speaking Switzerland, during which CPR was discussed. Data were analysed in French with thematic and conversation analysis, and the extracts used for publication were translated into English. Results Mean patient age was 83.7 years; 53.5% were admitted for rehabilitation after surgery or traumatism. CPR was explained in 53.8% of the conversations. Most explanations were brief and concerned the technical procedures, mentioning only rarely potential outcome. With one exception, medical indication and prognosis of CPR did not feature in these explanations. Explanations occurred either before the patient's answer (as part of the question about CPR preferences) or after the patient's answer, generated by patients' indecision, misunderstanding and by the need to clarify answers. Discussion and conclusions The scarcity and simplicity of CPR explanations highlight a reluctance to have in‐depth discussions and reflect the assumption that CPR does not need explaining. Providing patients with accurate information about the outcomes and risks of CPR is incremental for reaching informed decisions and patient‐centred care. Patient contribution Patients were involved in the data collection stage of the study.

In this paper we argue that transparency of machine learning algorithms, just as explanation, can be defined at different levels of abstraction. We criticize recent attempts to identify the explanation of black box algorithms with making their decisions (post-hoc) interpretable, focusing our discussion on counterfactual explanations. These approaches to explanation simplify the real nature of the black boxes and risk misleading the public about the normative features of a model. We propose a new form of algorithmic transparency, that consists in explaining algorithms as an intentional product, that serves a particular goal, or multiple goals (Daniel Dennet’s design stance) in a given domain of applicability, and that provides a measure of the extent to which such a goal is achieved, and evidence about the way that measure has been reached. We call such idea of algorithmic transparency “design publicity.” We argue that design publicity can be more easily linked with the justification of the use and of the design of the algorithm, and of each individual decision following from it. In comparison to post-hoc explanations of individual algorithmic decisions, design publicity meets a different demand (the demand for impersonal justification) of the explainee. Finally, we argue that when models that pursue justifiable goals (which may include fairness as avoidance of bias towards specific groups) to a justifiable degree are used consistently, the resulting decisions are all justified even if some of them are (unavoidably) based on incorrect predictions. For this argument, we rely on John Rawls’s idea of procedural justice applied to algorithms conceived as institutions.

BackgroundArtificial intelligence (AI)–driven symptom checkers are available to millions of users globally and are advocated as a tool to deliver health care more efficiently. To achieve the promoted benefits of a symptom checker, laypeople must trust and subsequently follow its instructions. In AI, explanations are seen as a tool to communicate the rationale behind black-box decisions to encourage trust and adoption. However, the effectiveness of the types of explanations used in AI-driven symptom checkers has not yet been studied. Explanations can follow many forms, including why-explanations and how-explanations. Social theories suggest that why-explanations are better at communicating knowledge and cultivating trust among laypeople.ObjectiveThe aim of this study is to ascertain whether explanations provided by a symptom checker affect explanatory trust among laypeople and whether this trust is impacted by their existing knowledge of disease.MethodsA cross-sectional survey of 750 healthy participants was conducted. The participants were shown a video of a chatbot simulation that resulted in the diagnosis of either a migraine or temporal arteritis, chosen for their differing levels of epidemiological prevalence. These diagnoses were accompanied by one of four types of explanations. Each explanation type was selected either because of its current use in symptom checkers or because it was informed by theories of contrastive explanation. Exploratory factor analysis of participants’ responses followed by comparison-of-means tests were used to evaluate group differences in trust.ResultsDepending on the treatment group, two or three variables were generated, reflecting the prior knowledge and subsequent mental model that the participants held. When varying explanation type by disease, migraine was found to be nonsignificant (P=.65) and temporal arteritis, marginally significant (P=.09). Varying disease by explanation type resulted in statistical significance for input influence (P=.001), social proof (P=.049), and no explanation (P=.006), with counterfactual explanation (P=.053). The results suggest that trust in explanations is significantly affected by the disease being explained. When laypeople have existing knowledge of a disease, explanations have little impact on trust. Where the need for information is greater, different explanation types engender significantly different levels of trust. These results indicate that to be successful, symptom checkers need to tailor explanations to each user’s specific question and discount the diseases that they may also be aware of.ConclusionsSystem builders developing explanations for symptom-checking apps should consider the recipient’s knowledge of a disease and tailor explanations to each user’s specific need. Effort should be placed on generating explanations that are personalized to each user of a symptom checker to fully discount the diseases that they may be aware of and to close their information gap.

Although Analytical Sociology is not often used in the mainstream Sociology, its history is however, traceable to the classical works of scholars such as Emile Durkheim, Max Weber, Alexis de Tocqueville as well as contemporary sociological thinkers like Talcott Parsons and Robert Merton, among others. This paper provides a contemporary argument for the application of mechanistic explanation in the overall understanding of Analytical Sociology using relevant and practical examples. In the course of this, attention has been paid to the concept of explanation and its various types in a sociological discourse. This paper therefore argues that social reality can significantly be understood only when explanations are systematic and detailed in content and context. The conclusion is that analytical sociology has the capacity to explain the actions of social actors within the social environment beyond some social doubts, even though, not all situations, can be sufficiently explained with the strategy.

People often offer an excuse or an apology after they do something wrong in an attempt to mitigate any potential negative consequences. In this paper, we examine how individuals employ social accounts when explaining their interpersonal transgression of meeting lateness to others in actual work settings. We examined the different combinations of social accounts and the social outcomes (forgiveness, helping behaviors, and intentions to continue interaction) of being late to a meeting. Across two studies using complementary experimental and survey methods, we found that a majority of late arrivers’ explanations included remorse and that including remorse significantly influences helping behaviors. Furthermore, we found no interaction between excuses and offering remorse. Implications of these findings and future directions are discussed.

Recent research claims that information cues and system attributes of algorithmic decision-making processes affect decision subjects’ fairness perceptions. However, little is still known about how these factors interact. This paper presents a user study (N = 267) investigating the individual and combined effects of explanations, human oversight, and contestability on informational and procedural fairness perceptions for high- and low-stakes decisions in a loan approval scenario. We find that explanations and contestability contribute to informational and procedural fairness perceptions, respectively, but we find no evidence for an effect of human oversight. Our results further show that both informational and procedural fairness perceptions contribute positively to overall fairness perceptions but we do not find an interaction effect between them. A qualitative analysis exposes tensions between information overload and understanding, human involvement and timely decision-making, and accounting for personal circumstances while maintaining procedural consistency. Our results have important design implications for algorithmic decision-making processes that meet decision subjects’ standards of justice.

Salt is consumed at too high levels in the general population, causing high blood pressure and related health problems. In this paper, we present results of ongoing research that tries to reduce salt intake via technology and in particular from an interface perspective. In detail, this paper features results of a study that examines the extent to which visual and textual explanations in a search interface can change salty food preferences. An online user study with 200 participants demonstrates that this is possible in food search results by accompanying recipes with a visual taste map that includes salt-replacer herbs and spices in the calculation of salty taste., 8 pages, 6 figures, HEALTHI workshop in conjunction with the ACM IUI conference

Salt is consumed at too high levels in the general population, causing high blood pressure and related health problems. In this paper, we present results of ongoing research that tries to reduce salt intake via technology and in particular from an interface perspective. In detail, this paper features results of a study that examines the extent to which visual and textual explanations in a search interface can change salty food preferences. An online user study with 200 participants demonstrates that this is possible in food search results by accompanying recipes with a visual taste map that includes salt-replacer herbs and spices in the calculation of salty taste.

International audience; In this paper we examine the efforts of one teacher working to improve her students' communication skills as part of a collaborative project with teachers and teacher educators/researchers. The paper reports on a project meeting where the teacher presents a short video clip featuring two student explanations. Yet only one explanation is treated in the lesson as an example of good communication. Following discussion and multiple re-viewings of the video clip in the meeting, what counts as good communication is critiqued by the teachers. Driven by an emphasis on the two-way nature of communication, the need for joint sense-making between teacher and students, and privileging explanations that communicate mathematical understanding, alternative teacher actions are suggested during the meeting that are related to how different teachers interpreted the students' explanation.

PurposeThe purpose of this paper is to raise attention within the records management community about evolving demands for explanations that make it possible to understand the content of records, also when they reflect output from algorithms.Design/methodology/approachThe methodological approach is a conceptual analysis based in records management theory and the philosophy of science. The concepts that are developed are thereafter applied to “the right to an explanation” and “an algorithmic ethics approach,” respectively, to further examine their viability.FindingsDifferent forms of explanations, ranging from “certain” explanations to predictions, as well as varying degrees of control over the input data to algorithms, affect the nature of the explanations and what kinds of records the explanations may reside in.Originality/valueThis paper contributes to a conceptual frame for discussing where explanations to algorithms may be documented, within different kinds of records, emanating from different kinds of processes.

Collaborative filtering is a widely used recommendation technique, which often relies on rating information shared by users, i.e., crowdsourced data. These filters rely on predictive algorithms, such as, memory or model based predictors, to build direct or latent user and item profiles from crowdsourced data. To predict unknown ratings, memory-based approaches rely on the similarity between users or items, whereas model-based mechanisms explore user and item latent profiles. However, many of these filters are opaque by design, leaving users with unexplained recommendations. To overcome this drawback, this paper introduces Explug, a local model-agnostic plug-in that works alongside stream-based collaborative filters to reorder and explain recommendations. The explanations are based on incremental user Trust & Reputation profiling and co-rater relationships. Experiments performed with crowdsourced data from TripAdvisor show that Explug explains and improves the quality of stream-based collaborative filter recommendations.

The same-decision probability (SDP) is a confidence measure for threshold-based decisions. In this paper we detail various properties of the SDP that allow for studying its robustness to changes in the threshold value upon which a decision is based. In addition to expressing confidence in a decision, the SDP has proven to be a useful tool in other contexts, such as that of information gathering. We demonstrate that the properties of the SDP as established in this paper allow for its application in the context of explaining Bayesian network classifiers as well.

The same-decision probability (SDP) is a confidence measure for threshold-based decisions. In this paper we detail various properties of the SDP that allow for studying its robustness to changes in the threshold value upon which a decision is based. In addition to expressing confidence in a decision, the SDP has proven to be a useful tool in other contexts, such as that of information gathering. We demonstrate that the properties of the SDP as established in this paper allow for its application in the context of explaining Bayesian network classifiers as well.

The same-decision probability (SDP) is a confidence measure for threshold-based decisions. In this paper we detail various properties of the SDP that allow for studying its robustness to changes in the threshold value upon which a decision is based. In addition to expressing confidence in a decision, the SDP has proven to be a useful tool in other contexts, such as that of information gathering. We demonstrate that the properties of the SDP as established in this paper allow for its application in the context of explaining Bayesian network classifiers as well.

Advances in artificial intelligence, sensors and big data man-agement have far-reaching societal impacts. As these sys-tems augment our everyday lives, it becomes increasingly important for people to understand them and remain in con-trol. We investigate how HCI researchers can help to develop accountable systems by performing a literature analysis of 289 core papers on explanations and explainable systems, as well as 12,412 citing papers. Using topic modeling, co-oc-currence and network analysis, we mapped the research space from diverse domains, such as algorithmic accounta-bility, interpretable machine learning, context-awareness, cognitive psychology, and software learnability. We reveal fading and burgeoning trends in explainable systems, and identify domains that are closely connected or mostly iso-lated. The time is ripe for the HCI community to ensure that the powerful new autonomous systems have intelligible in-terfaces built-in. From our results, we propose several impli-cations and directions for future research towards this goal.

This paper presents a rapid throwaway prototyping technique using Semantic Web technologies that product owners can use to gain valuable insight by quickly experiencing demonstrations of inconsistencies so that the functions present in the resulting end system can be tested. The product owner or client can then determine whether this behaviour matches their expectations. An inconsistency is triggered by a collection of data that violate a rule defined by the developer, indicating that some of the data must be removed. The technique quickly demonstrates how the application of a given logical inconsistency determines system behaviour. Developers can use this to demonstrate the effect of inconsistencies, allowing them to determine whether the inconsistency triggers an interaction with the end user so that the user can be informed. This rapid prototyping technique contributes to the existing body of literature on the Semantic Web. It can also be implemented together with existing software development methodologies to produce systems that better match the expectations of stakeholders. The rapid prototyping technique is applied in use cases to evaluate its effectives in demonstrating inconsistencies.

Inconsistency-tolerant semantics have been proposed to provide meaningful query answers even in the presence of inconsistent knowledge. Recently, explainability has also become a prominent problem in different areas of AI. While the complexity of inconsistency-tolerant semantics is rather well-understood, not much attention has been paid yet to the problem of explaining query answers when inconsistencies may exist. Recent work on existential rules in the inconsistent setting has focused only on understanding why a query is entailed. In this paper, we address another important problem, which is explaining why a query is not entailed under an inconsistency-tolerant semantics. In particular, we consider three popular semantics, namely, the ABox repair, the intersection of repairs, and the intersection of closed repairs. We provide a thorough complexity analysis for a wide range of existential rule languages and for several complexity measures.

Ontology-mediated query answering is an extensively studied paradigm, which aims at improving query answers with the use of a logical theory. In this paper, we focus on ontology languages based on existential rules, and we carry out a thorough complexity analysis of the problem of explaining query answers in terms of minimal subsets of database facts and related tasks

Querying inconsistent knowledge bases is a problem that has attracted a great deal of interest over the last decades. While several semantics of query answering have been proposed, and their complexity is rather well-understood, little attention has been paid to the problem of explaining query answers. Explainability has recently become a prominent problem in different areas of AI. In particular, explaining query answers allows users to understand not only what is entailed by an inconsistent knowledge base, but also why. In this paper, we address the problem of explaining query answers for existential rules under three popular inconsistency-tolerant semantics, namely, the ABox repair, the intersection of repairs, and the intersection of closed repairs semantics. We provide a thorough complexity analysis for a wide range of existential rule languages and for different complexity measures.

To help students acquire mathematics and science knowledge and competencies, educators typically use multiple external representations (MERs). There has been considerable interest in examining ways to present, sequence, and combine MERs. One prominent approach is the concreteness fading sequence, which posits that instruction should start with concrete representations and progress stepwise to representations that are more idealized. Various researchers have suggested that concreteness fading is a broadly applicable instructional approach. In this theoretical paper, we conceptually analyze examples of concreteness fading in the domains of mathematics, physics, chemistry, and biology and discuss its generalizability. We frame the analysis by defining and describing MERs and their use in educational settings. Then, we draw from theories of analogical and relational reasoning to scrutinize the possible cognitive processes related to learning with MERs. Our analysis suggests that concreteness fading may not be as generalizable as has been suggested. Two main reasons for this are discussed: (1) the types of representations and the relations between them differ across different domains, and (2) the instructional goals between domains and subsequent roles of the representations vary.

Summary Stable operation of an electric power system requires strict operational limits for the grid frequency. Fluctuations and external impacts can cause large frequency deviations and increased control efforts. Although these complex interdependencies can be modeled using machine learning algorithms, the black box character of many models limits insights and applicability. In this article, we introduce an explainable machine learning model that accurately predicts frequency stability indicators for three European synchronous areas. Using Shapley additive explanations, we identify key features and risk factors for frequency stability. We show how load and generation ramps determine frequency gradients, and we identify three classes of generation technologies with converse impacts. Control efforts vary strongly depending on the grid and time of day and are driven by ramps as well as electricity prices. Notably, renewable power generation is central only in the British grid, while forecasting errors play a major role in the Nordic grid., Graphical abstract, Highlights • Power grid frequency stability is analyzed via explainable artificial intelligence • Effect of generation ramps differ between Continental Europe, Britain, Nordic grids • Control efforts are driven by electricity prices and load ramps • Renewable generation and forecasting errors dominate Britain and Nordic grids, The bigger picture The transition to a sustainable energy system is challenging for the operation and stability of electric power systems as power generation becomes increasingly uncertain, grid loads increase, and their dynamical properties fundamentally change. At the same time, operational data are available at an unprecedented level of detail, enabling new methods of monitoring and control. To fully harness these data, advanced methods from machine learning must be used. In this paper, we present explainable artificial intelligence (XAI) as a tool to quantify, predict, and explain essential aspects of power system operation and stability in three major European synchronous areas. We focus on the power grid frequency, which measures the balance of generation and load and thus provides the central observable for control and balancing. Combining XAI with domain knowledge, we identify the main drivers and stability risks, while our model and open dataset may enable further XAI research on power systems., The transition to a sustainable energy system is one of the greatest challenges of our time. With operational data becoming available at an unprecedented level of detail, advanced methods from machine learning must be used to fully harness these data.In our article, we present explainable artificial intelligence (XAI) as a tool to quantify, predict, and explain essential aspects of power system operation and stability in three major European areas, giving indications of how to stably operate future power systems.

In our current society, it is very common to have access to a huge amount of information and scenarios in which it is possible to choose among a great number of alternatives. Therefore, systems that automate or assist with the decision-making process are becoming crucial. Those systems should allow users to represent their preferences accurately, even in scenarios where the user has many forms of comparing the available alternatives. In this paper, we propose an argument-based framework for multi-criteria decision-making based on conditional rules, that allows users to encode their preferences among the comparison criteria in terms of requirement and tolerance values. From these rules, arguments that are involved in the comparison process are generated. In order to comply with users’ demands for explanations of the given answers, our proposed framework can provide qualitative explanations about the argumentation process, and also an explanatory graph that shows how all the alternatives were ranked and the connections with the user's rules that were used. We also show the results of an empirical analysis of the performance of a developed prototype. Fil: Buron Brarda, Martín Ezequiel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina Fil: Tamargo, Luciano Héctor. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina Fil: García, Alejandro Jorge. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentina

This paper provides an extensive overview of the use of knowledge graphs in the context of Explainable Machine Learning. As of late, explainable AI has become a very active field of research by addressing the limitations of the latest machine learning solutions that often provide highly accurate, but hardly scrutable and interpretable decisions. An increasing interest has also been shown in the integration of Knowledge Representation techniques in Machine Learning applications, mostly motivated by the complementary strengths and weaknesses that could lead to a new generation of hybrid intelligent systems. Following this idea, we hypothesise that knowledge graphs, which naturally provide domain background knowledge in a machine-readable format, could be integrated in Explainable Machine Learning approaches to help them provide more meaningful, insightful and trustworthy explanations. Using a systematic literature review methodology we designed an analytical framework to explore the current landscape of Explainable Machine Learning. We focus particularly on the integration with structured knowledge at large scale, and use our framework to analyse a variety of Machine Learning domains, identifying the main characteristics of such knowledge-based, explainable systems from different perspectives. We then summarise the strengths of such hybrid systems, such as improved understandability, reactivity, and accuracy, as well as their limitations, e.g. in handling noise or extracting knowledge efficiently. We conclude by discussing a list of open challenges left for future research.

[EN] The massive presence of online learning resources leads many students to have more information than they can consume efficiently. Therefore, students do not always find adaptive learning material for their needs and preferences. In this paper, we present a Conversational Educational Recommender System (C-ERS), which helps students in the process of finding the more appropriated learning resources considering their learning objectives and profile. The recommendation process is based on an argumentation-based approach that selects the learning objects that allow a greater number of arguments to be generated to justify their suitability. Our system includes a simple and intuitive communication interface with the user that provides an explanation to any recommendation. This allows the user to interact with the system and accept or reject the recommendations, providing reasons for such behavior. In this way, the user is able to inspect the system's operation and understand the recommendations, while the system is able to elicit the actual preferences of the user. The system has been tested online with a real group of undergraduate students in the Universidad Nacional de Colombia, showing promising results., This work was partially supported by MINECO/FEDER RTI2018-095390-B-C31 project of the Spanish government, and by the Generalitat Valenciana (PROMETEO/2018/002) project.

Ontology-mediated query answering is a paradigm that seeks to exploit the semantic knowledge expressed in terms of ontologies to improve query answers over incomplete data sources. In this paper, we focus on description logic ontologies, and study the problem of explaining why an ontology-mediated query is entailed from a given data source. Specifically, we view explanations as minimal sets of assertions from an ABox, which satisfy the ontologymediated query. Based on such explanations, we study a variety of problems taken from the recent literature on explanations (studied for existential rules), such as recognizing all minimal explanations. Our results establish tight connections between intractable explanation problems and variants of propositional satisfiability problems. We provide insights on the inherent computational difficulty of deriving explanations for ontology-mediated queries.

Providing explanations based on user reviews in recommender systems may increase users’ perception of transparency. However, little is known about how these explanations should be presented to users in order to increase both their understanding and acceptance. We present in this paper a user study to investigate the effect of different display styles (visual and text only) on the perception of review-based explanations for recommended hotels. Additionally, we also aim to test the differences in users’ perception when providing information about their own profiles, in addition to a summarized view on the opinions of other users about the recommended hotel. Our results suggest that the perception of explanations regarding these aspects may vary depending on user characteristics, such as decision-making styles or social awareness.

In some scenarios, like music or tourism, people often consume items in groups. However, reaching a consensus is difficult as different members of the group may have highly diverging tastes. To keep the rest of the group satisfied, an individual might need to be confronted occasionally with items they do not like. In this context, presenting an explanation of how the system came up with the recommended item(s), may make it easier for users to accept items they might not like for the benefit of the group. This paper presents our progress on proposing improved algorithms for recommending items (for both music and tourism) for a group to consume and an approach for generating natural language explanations. Our future directions include extending the current work by modelling different factors that we need to consider when we generate explanations for groups e.g. size of the group, group members' personality, demographics, and their relationship.

This paper outlines the model-based theory of causal reasoning. It postulates that the core meanings of causal assertions are deterministic and refer to temporally-ordered sets of possibilities: A causes B to occur means that given A, B occurs, whereas A enables B to occur means that given A, it is possible for B to occur. The paper shows how mental models represent such assertions, and how these models underlie deductive, inductive, and abductive reasoning yielding explanations. It reviews evidence both to corroborate the theory and to account for phenomena sometimes taken to be incompatible with it. Finally, it reviews neuroscience evidence indicating that mental models for causal inference are implemented within lateral prefrontal cortex.

Contains fulltext : 234229.pdf (Publisher’s version ) (Open Access) Research in the social sciences has shown that expectations are an important factor in explanations as used between humans: rather than explaining the cause of an event per se, the explainer will often address another event that did not occur but that the explainee might have expected. For AI-powered systems, this finding suggests that explanation-generating systems may need to identify such end user expectations. In general, this is a challenging task, not the least because users often keep them implicit; there is thus a need to investigate the importance of such an ability. In this paper, we report an empirical study with 181 participants who were shown outputs from a text classifier system along with an explanation of why the system chose a particular class for each text. Explanations were both factual, explaining why the system produced a certain output or counterfactual, explaining why the system produced one output instead of another. Our main hypothesis was explanations should align with end user expectations; that is, a factual explanation should be given when the system's output is in line with end user expectations, and a counterfactual explanation when it is not. We find that factual explanations are indeed appropriate when expectations and output match. When they do not, neither factual nor counterfactual explanations appear appropriate, although we do find indications that our counterfactual explanations contained at least some necessary elements. Overall, this suggests that it is important for systems that create explanations of AI systems to infer what outputs the end user expected so that factual explanations can be generated at the appropriate moments. At the same time, this information is, by itself, not sufficient to also create appropriate explanations when the output and user expectations do not match. This is somewhat surprising given investigations of explanations in the social sciences, and will need more scrutiny in future studies. 27 p.

The paper documents beliefs that manifest themselves through newspaper items and elaborates on their potential to enhance a sustainable learning environment in a school science lesson. “Learning environment” is depicted from different angles and includes virtual and real learning environments, school environments and classroom environments. Descriptive and item analyses were conducted on sixty-eight newspaper items that were identified. The nature of problems and prescriptions/solutions was categorised for each item and the paper further provides elaboration on the types of problems and recommended solutions. The results show that the “believed” structure contents in their newspaper items to catch the attention of the “believer”. Lessons on the power of belief must be learnt by school science teachers if they are to succeed in creating a sustainable learning environment with improved performance in school science.

The main purpose of this paper is to present Slovenian and Finnish prospective chemistry teachers? perceptions of their future profession, especially with regard to their understanding of the role of the triple nature of chemical concepts (macro, submicro and symbolic) and their representations in chemistry learning. A total of 19 prospective teachers (10 Slovenian, 9 Finnish) at master?s level in chemical education participated in the research. The prospective teachers? opinions were gathered using an electronic questionnaire comprising six open-ended questions. The study revealed many parallels between Slovenian and Finnish prospective chemistry teachers? perceptions of their future profession and their understanding of the role of the triple nature of chemical concepts, especially particle representations, in chemistry learning. The majority of the prospective teachers from both countries believe that personal characteristics are the most important attribute of a successful chemistry teacher. Thus, they highly value teachers? enthusiasm for teaching and the use of contemporary teaching approaches in chemistry. The prospective teachers displayed an adequate understanding of the role of the triple nature of chemical concepts (i.e., particle representations) in the planning and implementation of a specific chemistry lesson.

ResumenLas explicaciones en los sistemas de recomendación se han utilizado para mejorar componentes de la experiencia del usuario (EU). Se ha probado que las explicaciones son útiles para mejorar la percepción del usuario respecto a la satisfacción, y para persuadir al usuario de adoptar el sistema de recomendación. Este artículo se enfoca en la evaluación de la confianza del usuario de acuerdo con el sistema y sus relaciones con la comprensión y esfuerzo cognitivo que percibe, mediante el uso de explicaciones en un tipo específico de sistema de recomendación: sensible al contexto. Se realizó un experimento de usuario con un sistema de recomendación organizacional que provee recomendaciones de personas, lugares, eventos, objetos de conocimiento e infraestructura, usando tres tipos de explicación: mapas conceptuales, mapas mentales y explicaciones textuales. Los resultados muestran que, aunque los mapas conceptuales y mentales incrementan la comprensión de las recomendaciones y reducen el esfuerzo cognitivo percibido, las explicaciones textuales mejoran la confianza del usuario respecto al sistema, aun cuando requieren mayor esfuerzo cognitivo para comprenderlas.AbstractExplanations on recommender systems have been used to improve components of user experience. It has been proven that explanations are useful to enhance users’ perception on satisfaction and persuade users to adopt the recommender system. This paper focuses on evaluating user trust and the trade-offs with understandability and cognitive effort by using explanations in a specific type of recommender system: context-aware. We performed an user experiment with an organizational recommender system that gives recommendations of people, places, events, knowledge objects and infrastructure, using three different types of explanations: conceptual maps, mind maps and textual explanation. The results show that although mind and conceptual maps increases users’ understanding of recommendations and decreases cognitive effort, textual explanations improves the users’ trust on the system even when they require much cognitive effort to be understood.

Ontology-mediated query answering is an extensively studied paradigm, which aims at improving query answers with the use of a logical theory. As a form of logical entailment, ontology-mediated query answering is fully interpretable, which makes it possible to derive explanations for query answers. Surprisingly, however, explaining answers for ontology-mediated queries has received little attention for ontology languages based on existential rules. In this paper, we close this gap, and study the problem of explaining query answers in terms of minimal subsets of database facts. We provide a thorough complexity analysis for several decision problems associated with minimal explanations under existential rules.

Museum educators play a key role in explaining science in a museum. Verbal language is primarily used to communicate scientific concepts, but the way language shapes the explanations provided has not been investigated. This qualitative study focuses on the explanations about light provided by three museum educators to eighth grade students (13–14 years old), during unstructured visits to a science museum. The visits were audio‐recorded and field notes were taken. The museum educators' language was analyzed at a microlevel, through the perspective of Cognitive Linguistics and Conceptual Metaphor theory. The results of this analysis coupled with a multidimensional framework for analyzing explanations allowed an understanding on what is explained and how it is explained in the museum by museum educators. Findings show that explanations were descriptive and causal, structured by the use of hybrid lexicon and by conceptual metaphors, whose quality depends on the structural similarity between domains. Furthermore, the explanations based on geometric optics were qualitative and with low level of precision, complexity, and abstractness., The contribution of Ana Sofia Afonso to this paper is funded by CIEd—Research Center on Education, projects UID/CED/1661/2013 and UID/CED/1661/2016, Institute of Education, University of Minho, through national funds of FCT/MCTESPT

In this paper we consider an interactive and explanation based dialogue approach to complex and `wicked' planning problems. Wicked problems are essentially imprecisely formulated problems having no clearly defined goals and constraints. The dialogue approach is aimed at reducing the problem complexity during interaction with the human expert. The involved software agents are mostly optimization procedures. The approach contains the following steps: (1) Selection of a specific concern in a proposed solution; (2) Calculation of a stakeholder defined ideal plan; and (3) Comparing the actually generated plan and the prototype based on a similarity measure. The comparison of the actual and the ideal plan looks at aspects of interest for the stakeholder such as resource consumptions or structural properties of the plan. The proposed approach is generic and was applied and customized to three classes of wicked problems: release planning, investment planning, and urban planning. All three applications are described and illustrated in the paper.

International audience; We pursue an investigation of data-driven collaborative work-flows. In the model, peers can access and update local data, causing side-e↵ects on other peers' data. In this paper, we study means of explaining to a peer her local view of a global run, both at runtime and statically. We consider the notion of " scenario for a given peer " that is a subrun observationally equivalent to the original run for that peer. Because such a scenario can sometimes di↵er significantly from what happens in the actual run, thus providing a misleading explanation , we introduce and study a faithfulness requirement that ensures closer adherence to the global run. We show that there is a unique minimal faithful scenario, that explains what is happening in the global run by extracting only the portion relevant to the peer. With regard to static explanations, we consider the problem of synthesizing, for each peer, a " view program " whose runs generate exactly the peer's observations of the global runs. Assuming some conditions desirable in their own right, namely transparency and boundedness, we show that such a view program exists and can be synthesized. As an added benefit, the view program rules provide provenance information for the updates observed by the peer.`

An important task for recommender system is to generate explanations according to a user's preferences. Most of the current methods for explainable recommendations use structured sentences to provide descriptions along with the recommendations they produce. However, those methods have neglected the review-oriented way of writing a text, even though it is known that these reviews have a strong influence over user's decision. In this paper, we propose a method for the automatic generation of natural language explanations, for predicting how a user would write about an item, based on user ratings from different items' features. We design a character-level recurrent neural network (RNN) model, which generates an item's review explanations using long-short term memories (LSTM). The model generates text reviews given a combination of the review and ratings score that express opinions about different factors or aspects of an item. Our network is trained on a sub-sample from the large real-world dataset BeerAdvocate. Our empirical evaluation using natural language processing metrics shows the generated text's quality is close to a real user written review, identifying negation, misspellings, and domain specific vocabulary., Comment: 7 pages, 5 figures, 2nd workshop on Deep Learning for Recommender Systems

In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness sometimes at the cost of scarifying accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, delineating explicitly or implicitly its own definition of interpretability and explanation. The aim of this paper is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective., This work is currently under review on an international journal

Part 5: MAKE Explainable AI; International audience; The transparent AI initiative has ignited several academic and industrial endeavors and produced some impressive technologies and results thus far. Many state-of-the-art methods provide explanations that mostly target the needs of AI engineers. However, there is very little work on providing explanations that support the needs of business owners, software developers, and consumers who all play significant roles in the service development and use cycle. By considering the overall context in which an explanation is presented, including the role played by the human-in-the-loop, we can hope to craft effective explanations. In this paper, we introduce the notion of the “cognitive value” of an explanation and describe its role in providing effective explanations within a given context. Specifically, we consider the scenario of a business owner seeking to improve sales of their product, and compare explanations provided by some existing interpretable machine learning algorithms (random forests, scalable Bayesian Rules, causal models) in terms of the cognitive value they offer to the business owner. We hope that our work will foster future research in the field of transparent AI to incorporate the cognitive value of explanations in crafting and evaluating explanations.

Resumo Explicar é uma das práticas discursivas mais importantes da ciência e do seu ensino. Nas últimas décadas, este tema passou a receber atenção de legislações educacionais, professores e pesquisadores, embora pesquisas sobre o uso de explicações no ensino de ciências destaquem a dificuldade de definir este conceito. Neste trabalho, revisamos o conceito explicação a partir de três distinções básicas: explicações e narrativas; explicações e argumentos; explicações científicas e explicações escolares. Este trabalho busca primeiramente trazer clareza para os conceitos aqui discutidos, enfatizando que explicações, argumentos e narrativas são elementos importantes, porém distintos da comunicação da sala de aula. Limites para a aproximação entre práticas explicativas com argumentos e narrativas são discutidos. O trabalho aponta também a importância do tema para o ensino de ciências e o baixo número de trabalhos dedicados a esta questão entre pesquisadores brasileiros. Abstract Explaining is among the most important discursive practice for science and its teaching. In the last decades this topic received attention from official documents, teachers and researchers. However, research in science teaching highlights the difficulty in defining this concept. In this paper we review the concept of explanation from three basic perspectives: explanations and narratives; explanation and arguments; scientific explanation and school science explanation. This work seeks firstly to bring clarity to the above-mentioned concepts, highlighting the fact that explanation, arguments and narratives are important but distinct elements of science classroom discourse. Limits in explanatory practices in relation to arguments and narratives are discussed. It also shows the importance of the topic for science teaching and the lack of research on explanations in Brazilian literature.

In some scenarios, like music, people often consume items in groups. However, reaching a consensus is difficult, and often compromises need to be made. Such compromises can potentially help users expand their tastes. They can also lead to outright rejection of the recommended items. One way to avoid this is to explain recommendations that are surprising, or even expected to be disliked, by an individual user. This paper presents an approach for generating explanations for groups. We propose algorithms for selecting a sequence of songs for a group to consume. These algorithms consider consensus but have different trade-offs. Next, using these algorithms we generated explanations in a layered evaluation using synthetic data. We studied the influence of these explanations in structured interviews with users (n=16) on user satisfaction.

When a group is traveling together it is challenging to recommendan itinerary consisting of several points of interest (POIs). Thepreferences of individual group members often diverge, but it isimportant to keep everyone in the group satisfied during the entiretrip. We propose a method to consider the preferences of all thepeople in the group. Building on this method, we design expla-nations for groups of people, to help them reach a consensus forplaces to visit. However, one open question is how to best formu-late explanations for such sequences. In this paper, we introduceTourExplain, an automated crowdsourcing pipeline to generate andevaluate explanations for groups with the aim of improving ourinitial proposed explanations by relying on the wisdom of crowds.

Neural Networks have been utilized to solve various tasks such as image recognition, text classification, and machine translation and have achieved exceptional results in many of these tasks. However, understanding the inner workings of neural networks and explaining why a certain output is produced are no trivial tasks. Especially when dealing with text classification problems, an approach to explain network decisions may greatly increase the acceptance of neural network supported tools. In this paper, we present an approach to visualize reasons why a classification outcome is produced by convolutional neural networks by tracing back decisions made by the network. The approach is applied to various text classification problems, including our own requirements engineering related classification problem. We argue that by providing these explanations in neural network supported tools, users will use such tools with more confidence and also may allow the tool to do certain tasks automatically.

Graph navigational languages allow to specify pairs of nodes in a graph subject to the existence of paths satisfying a certain regular expression. Under this evaluation semantics, connectivity information in terms of intermediate nodes/edges that contributed to the answer is lost. The goal of this paper is to introduce the GeL language, which provides query evaluation semantics able to also capture connectivity information and output graphs. We show how this is useful to produce query explanations. We present efficient algorithms to produce explanations and discuss their complexity. GeL machineries are made available into existing SPARQL processors thanks to a translation from GeL queries into CONSTRUCT SPARQL queries. We outline examples of explanations obtained with a tool implementing our framework and report on an experimental evaluation that investigates the overhead of producing explanations.

Myriad research establishes that Easterners think more holistically (i.e., attend to the “big picture” of how the world fits together and rely more on intuition) than Westerners do. Yet little is known about how Easterners integrate, structure, and make sense the information gleaned through holistic thinking. This paper proposes that, compared to Westerners, Easterners may rely more on analogical reasoning to integrate information and gain a sense of understanding their worlds. Four studies provide evidence that Easterners rely more on analogical reasoning that Westerners do. Compared to Westerners, Easterners found it easier to generate analogical explanations for understanding an outcome, preferred analogical to non-analogical explanations, showed some evidence of being more likely to spontaneously apply analogical solutions to the Duncker ray tumor problem, and tended to use more individual analogies in cultural products like children’s stories. Easterners, however, did not show evidence of being better at highly structured analogical reasoning (e.g., the Raven’s matrices) than Westerners. These findings suggest that Easterners and Westerners may both be able to reason analogically when required, but Easterners may spontaneously rely more on analogical reasoning to gain a sense of understanding of the world.

International audience; Children as young as 4-5 years can produce descriptive narratives but have been found to have difficulties to talk about causal and mind-oriented aspects of the story, such as the characters’ intentions and beliefs, or their different viewpoints. This paper considers whether the first narrative produced by the children represents the developmental limit of their competencies or whether children can be brought to produce more complex mind-oriented narratives through a simple procedure by which children are requested to focus on the causes of the story events, This question was investigated by presenting a sequence of five wordless pictures (the “stone story”) to 120 French-speaking children aged 5 to 10 years who narrated to the experimenter their first narrative. Then, 60 children participated in the causal-oriented conversation and 60 children served as control group and played a memory game with the story images. Results show that after the causal-oriented conversation, from 6 years on, children produced more coherent and mind-oriented narratives than they did in their first narrative. These improvements were not found in the control group. Pragmatic and cognitive aspects are discussed as possible causes of these improvements. We highlight the importance for assessment and remediation of the conversational procedure and of the resulting intra-individual variation.

Este documento presenta los resultados de una experiencia con profesores en formación inicial del Proyecto Curricular de Licenciatura en Química de la Universidad Pedagógica Nacional, con quienes se desarrollaron unidades didácticas centradas en la explicación de fenómenos químicos cotidianos como estrategia para la formación de profesores de química, de las cuales se caracterizaron los niveles de representación químicos y la admisibilidad de las explicaciones construidas por los profesores en formación. Dicha iniciativa permitió consolidar un espacio que vinculó congruentemente aspectos disciplinares de la química con los de su didáctica, con el fin de aportar a sus integrantes recursos y metodologías para transformar las formas habituales de enseñanza, aprendizaje y evaluación de esta disciplina., This paper shows the research results obtained with a group of pre-service chemistry teachers at Universidad Pedagógica Nacional, employing didactic units focused in everyday chemistry as strategy for chemistry teaching. The explanations of pre-service chemistry teachers for the analyzed everyday chemical phenomena were characterized according to its admissibility and chemical levels of representation. The project allowed consolidating a space which employs coherently disciplinary and didactic aspects of chemistry, contributing to the pre-service teachers with resources and methodologies to transform the traditional forms of teaching, learning and evaluation of chemistry.

This paper aims to explain previously described increases in self-reported psychological distress between 1987 and 2006 among samples identical in respect of age (15 years), school year and geographical location (West of Scotland). Such increases might be explained by changes in exposure (changes in levels of risk or protective factors) and/or by changes in vulnerability (changes in the relationship between risk/protective factors and psychological distress). Key areas of social change over this time period allow identification of potential explanatory factors, categorised as economic, family, educational, values and lifestyle and represented by variables common to each study. Psychological distress was measured via the 12-item General Health Questionnaire, Likert scored. Analyses were conducted on those with complete data on all variables (N = 3276 of 3929), and separately for males and females. Between 1987 and 2006, levels of almost every potential explanatory factor changed in line with general societal trends. Associations between explanatory factors and GHQ tended to be stronger among females, and at the later date. The strongest associations were with worries, arguments with parents, and, at the later date, school disengagement. The factors which best accounted for the increase in mean GHQ between 1987 and 2006 were arguments with parents, school disengagement, worry about school and, for females, worry about family relationships, reflecting both increasing exposure and vulnerability to these risk factors. A number of limitations to our analysis can be identified. However, our results reinforce the conclusions of others in highlighting the role of family and educational factors as plausible explanations for increases in young people’s psychological distress.

The modelling of complex, dynamic and uncertain socioenvironmental systems requires close collaboration between research disciplines and stakeholders at all levels, for if such models are representations of aspects of reality, how can it be possible to build them without inputs from people who interact with the systems in reality? This paper reflects on findings of case study research involving stakeholders in knowledge creation through conceptual and formal model building to support upland water catchment management. The uncertainty, multiple scales and conflicting understandings of stakeholders inherent in natural resource management necessitate a strong focus on participatory processes in integrated modelling. This leads to the recognition that problems and solutions should be identified by the stakeholders themselves, emphasising the intersection and complementarity of lay and expert knowledge. Stakeholders in this context comprise varied groups such as land managers ( e. g. grouse moor managers and sheep farmers), water companies and water users, tourists, residents, policy-makers and researchers. Models are used at multiple stages to help formulate problems, create and compare conceptual understanding, and explore implications. This requires the involvement of stakeholders early in the problem formulation and research process to help answer the 'right' questions and provide 'relevant' outputs. This poses a number of interesting new challenges for the organisation of research. In contrast to traditional approaches of matching model components to expertise in the research team, modelling expertise must adapt to answer the questions and priorities that emerge from stakeholder engagement.