Search

Expert systems have had little impact as computing artifacts. In this paper we argue that the reason for this stems from the underlying assumption of most builders of expert systems that an expert system needs to acquire information and to control the interaction between the human user and itself. We show that this assumption has serious linguistic and usability flaws which diminish the likelihood of producing socially acceptable expert systems. We propose a reversal of this paradigm, for the design of expert systems, by assuming that it is the human user who needs to acquire information and to control the interaction between themselves and the system. [ABSTRACT FROM AUTHOR]

Companies frequently offer product recommendations to customers, according to various algorithms. This research explores how companies should frame the methods they use to derive their recommendations, in an attempt to maximize click-through rates. Two common framings—user-based and item-based—might describe the same recommendation. User-based framing emphasizes the similarity between customers (e.g., "People who like this also like..."); item-based framing instead emphasizes similarities between products (e.g., "Similar to this item"). Six experiments, including two field experiments within a mobile app, show that framing the same recommendation as user-based (vs. item-based) can increase recommendation click-through rates. The findings suggest that user-based (vs. item-based) framing informs customers that the recommendation is based on not just product matching but also taste matching with other customers. Three theoretically derived and practically relevant boundary conditions related to the recommendation recipient, the products, and other users also offer practical guidance for managers regarding how to leverage recommendation framings to increase recommendation click-throughs. [ABSTRACT FROM AUTHOR]

In recent years the use of complex machine learning has increased drastically. These complex black box models trade interpretability for accuracy. The lack of interpretability is troubling for, e.g., socially sensitive, safety-critical, or knowledge extraction applications. In this paper, we propose a new explanation method, SLISE, for interpreting predictions from black box models. SLISE can be used with any black box model (model-agnostic), does not require any modifications to the black box model (post-hoc), and explains individual predictions (local). We evaluate our method using real-world datasets and compare it against other model-agnostic, local explanation methods. Our approach solves shortcomings in other related explanation methods by only using existing data instead of sampling new, artificial data. The method also generates more generalizable explanations and is usable without modification across various data domains.

For critical operational decisions (e.g. consulting services), explanations and interpretable results of powerful Artificial Intelligence (AI) systems are becoming increasingly important. Knowledge graphs possess a semantic model that integrates heterogeneous information sources and represents knowledge elements in a machine-readable form. The integration of knowledge graphs and machine learning methods represents a new form of hybrid intelligent systems that benefit from each other's strengths. Our research aims at an explainable system with a specific knowledge graph architecture that generates human-understandable results even when no suitable domain experts are available. Against this background, the interpretability of a knowledge graph-based explainable AI approach for business process analysis is focused. We design a framework of interpretation, show how interpretable models are generated by a single case study and evaluate the applicability of our approach by different expert interviews. Result paths on weaknesses and improvement measures related to a business process are used to produce stochastic decision trees, which improve the interpretability of results. This can lead to interesting consulting self-services for clients or be applied as a device for accelerating classical consulting projects. [ABSTRACT FROM AUTHOR]

Income inequality is growing in many parts of the world and, for the poorest children in a society, is associated with multiple, negative, developmental outcomes. This review of the research literature considers how childrens' and adolescents' understanding of economic inequality changes with age. It highlights shifts in conceptual understanding (from 'having and not having', to social structural and moral explanations), moral reasoning and the impact of the agents of socialization from parents to the media and cultural norms and discourses. It also examines how social processes affect judgements and the importance of an emerging sense of self in relation to questions of economic inequality. Finally, the review covers methodological considerations and suggests pathways for future research. [ABSTRACT FROM AUTHOR]

This article introduces a network approach to describe the quality of written scientific explanations. Existing approaches evaluate explanations mainly on the level of sentences or as a whole but not on the elementary level of single terms. Moreover, evaluation of explanations is often based on highly inferential scoring techniques. We addressed both issues by converting the elementary structure of terms in explanations into networks (so-called element maps) and analysing these with mathematical measures, thus extracting the size and complexity of an explanation, adequacy, coherence, and use of key terms. A total of 65 explanations of experts and students were analysed quantitatively and qualitatively. Differences between expert and student maps' measures can be interpreted meaningfully against the background of existing research findings. Thus, we argue that our approach using network analysis provides a precise, fine-grained, and low-inferential tool that complements and refines existing approaches. Element maps have the potential to improve teaching and research by precisely revealing the strengths and weaknesses of explanations. [ABSTRACT FROM AUTHOR]

We propose answer-set programs that specify and compute counterfactual interventions on entities that are input on a classification model. In relation to the outcome of the model, the resulting counterfactual entities serve as a basis for the definition and computation of causality-based explanation scores for the feature values in the entity under classification, namely responsibility scores. The approach and the programs can be applied with black-box models, and also with models that can be specified as logic programs, such as rule-based classifiers. The main focus of this study is on the specification and computation of best counterfactual entities, that is, those that lead to maximum responsibility scores. From them one can read off the explanations as maximum responsibility feature values in the original entity. We also extend the programs to bring into the picture semantic or domain knowledge. We show how the approach could be extended by means of probabilistic methods, and how the underlying probability distributions could be modified through the use of constraints. Several examples of programs written in the syntax of the DLV ASP-solver, and run with it, are shown. [ABSTRACT FROM AUTHOR]

In this paper, we present a fundamental framework for defining different types of explanations of AI systems and the criteria for evaluating their quality. Starting from a structural view of how explanations can be constructed, i.e., in terms of an explanandum (what needs to be explained), multiple explanantia (explanations, clues, or parts of information that explain), and a relationship linking explanandum and explanantia, we propose an explanandum-based typology and point to other possible typologies based on how explanantia are presented and how they relate to explanandia. We also highlight two broad and complementary perspectives for defining possible quality criteria for assessing explainability: epistemological and psychological (cognitive). These definition attempts aim to support the three main functions that we believe should attract the interest and further research of XAI scholars: clear inventories, clear verification criteria, and clear validation methods. • We propose a framework for defining different types of explanations of AI systems. • We contextualize current XAI discourses within the proposed framework. • We highlight two broad perspectives for defining quality criteria for explainability. • We discuss the relevance of our framework in light of current and upcoming AI regulation. • We confer fundamental aspects for future research of XAI scholars. [ABSTRACT FROM AUTHOR]

Learning from instructional explanations is one of the most established, prevalent, and obvious ways of learning--but it carries the risk of shallow processing. Unlike previous research that focused on providing digital just-in-time support measures for learning with explanations, we strived to prepare learners on how to make the most of upcoming explanations. We thus developed a short-term computer-based training intervention on the focused processing of instructional explanations. In two experiments (N1 = 47, N2 = 42), we tested its effects on learning processes and outcomes of a subsequent learning phase. Our results revealed that the training intervention fostered domain-general knowledge about explanations. Furthermore, it enabled learners to benefit from future instructional explanations in other domains (inter-domain transfer for university students, Experiment 1) or at least on other topics (intra-domain transfer for primary school fourth graders, Experiment 2). The digital training intervention did not trigger more cognitive load in the subsequent learning phase. All in all, we describe an initial promising step toward a generic training effect that has the potential advantage of enhancing learning from explanations without altering the actual learning material. [ABSTRACT FROM AUTHOR]

Conviction Narrative Theory (CNT) is a theory of choice under radical uncertainty – situations where outcomes cannot be enumerated and probabilities cannot be assigned. Whereas most theories of choice assume that people rely on (potentially biased) probabilistic judgments, such theories cannot account for adaptive decision-making when probabilities cannot be assigned. CNT proposes that people use narratives – structured representations of causal, temporal, analogical, and valence relationships – rather than probabilities, as the currency of thought that unifies our sense-making and decision-making faculties. According to CNT, narratives arise from the interplay between individual cognition and the social environment, with reasoners adopting a narrative that feels "right" to explain the available data; using that narrative to imagine plausible futures; and affectively evaluating those imagined futures to make a choice. Evidence from many areas of the cognitive, behavioral, and social sciences supports this basic model, including lab experiments, interview studies, and econometric analyses. We identify 12 propositions to explain how the mental representations (narratives) interact with four inter-related processes (explanation, simulation, affective evaluation, and communication), examining the theoretical and empirical basis for each. We conclude by discussing how CNT can provide a common vocabulary for researchers studying everyday choices across areas of the decision sciences. [ABSTRACT FROM AUTHOR]

Nearly all diseases are caused by different combinations of exposures. Yet, most epidemiological studies focus on estimating the effect of a single exposure on a health outcome. We present the Causes of Outcome Learning approach (CoOL), which seeks to discover combinations of exposures that lead to an increased risk of a specific outcome in parts of the population. The approach allows for exposures acting alone and in synergy with others. The road map of CoOL involves (i) a pre-computational phase used to define a causal model; (ii) a computational phase with three steps, namely (a) fitting a non-negative model on an additive scale, (b) decomposing risk contributions and (c) clustering individuals based on the risk contributions into subgroups; and (iii) a post-computational phase on hypothesis development, validation and triangulation using new data before eventually updating the causal model. The computational phase uses a tailored neural network for the non-negative model on an additive scale and layer-wise relevance propagation for the risk decomposition through this model. We demonstrate the approach on simulated and real-life data using the R package 'CoOL'. The presentation focuses on binary exposures and outcomes but can also be extended to other measurement types. This approach encourages and enables researchers to identify combinations of exposures as potential causes of the health outcome of interest. Expanding our ability to discover complex causes could eventually result in more effective, targeted and informed interventions prioritized for their public health impact. [ABSTRACT FROM AUTHOR]

Traditional lectures are commonly understood to be a teacher-centered mode of instruction where the main aim is a provision of explanations by an educator to the students. Recent literature in higher education overwhelmingly depicts this mode of instruction as inferior compared to the desired student-centered models based on active learning techniques. First, using a four-quadrant model of educational environments, we address common confusion related to a conflation of two prevalent dichotomies by focusing on two key dimensions: (1) the extent to which students are prompted to engage actively and (2) the extent to which expert explanations are provided. Second, using a case study, we describe an evolution of tertiary mathematics education, showing how traditional instruction can still play a valuable role, provided it is suitably embedded in a student-centered course design. We support our argument by analyzing the teaching practice and learning environment in a third-year abstract algebra course through the lens of Stanislas Dehaene's theoretical framework for effective teaching and learning. The framework, comprising "four pillars of learning", is based on a state-of-the-art conception of how learning can be facilitated according to cognitive science, educational psychology and neuroscience findings. In the case study, we illustrate how, over time, the unit design and the teaching approach have evolved into a learning environment that aligns with the four pillars of learning. We conclude that traditional lectures can and do evolve to optimize learning environments and that the erection of the dichotomy "traditional instruction versus active learning" is no longer relevant. [ABSTRACT FROM AUTHOR]

This study explored whether different types of instructional visuals—knowledge maps and pictorial illustrations—encourage students to focus on specific types of conceptual relationships during learning. Undergraduates (n = 134) studied a text lesson on the human nervous system accompanied by maps (text-with-maps group), illustrations (text-with-illustrations group), or no visuals (text-only group). Then all students orally explained what they learned as if they were teaching a peer. The text-with-maps group generated more hierarchical relationships than the other two groups, and both visual groups generated more temporal relationships than the text-only group. The groups did not significantly differ in the number of structural relationships generated. On a subsequent post-test, only the text-with-maps group significantly outperformed the text-only group, and the two visual groups did not significantly differ from each other. These findings highlight how different visuals affect the types of relationships students focus on when learning from the same text. [ABSTRACT FROM AUTHOR]

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.

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.

In Semantic Web applications, reasoning engines that are data intensive commonly materialise inferences to speed up processing at query time. However, in evolving systems, such as smart environments, semantic-based context aware systems (SCAS) [6] or social software with user-generated data, knowledge does not grow monotonically: newer facts may contradict older ones, knowledge may be deprecated, discarded or updated such that knowledge must sometimes be retracted. We are describing a technique to retract explicit and inferred statements, when some information becomes obsolete, as well as retracting any statement that would lead to get back the removed explicit statements. This technique is based on OWL justifications and is triggered whenever a knowledge base becomes inconsistent, such that the system stays in a consistent state all the time, in spite of uncontrolled evolution. We prove termination and correctness of the algorithm, and describe the implementation and evaluation of the proposal. [ABSTRACT FROM AUTHOR]

The introduction of machine learning to small molecule research– an inherently multidisciplinary field in which chemists and data scientists combine their expertise and collaborate - has been vital to making screening processes more efficient. In recent years, numerous models that predict pharmacokinetic properties or bioactivity have been published, and these are used on a daily basis by chemists to make decisions and prioritize ideas. The emerging field of explainable artificial intelligence is opening up new possibilities for understanding the reasoning that underlies a model. In small molecule research, this means relating contributions of substructures of compounds to their predicted properties, which in turn also allows the areas of the compounds that have the greatest influence on the outcome to be identified. However, there is no interactive visualization tool that facilitates such interdisciplinary collaborations towards interpretability of machine learning models for small molecules. To fill this gap, we present CIME (ChemInformatics Model Explorer), an interactive web-based system that allows users to inspect chemical data sets, visualize model explanations, compare interpretability techniques, and explore subgroups of compounds. The tool is model-agnostic and can be run on a server or a workstation. [ABSTRACT FROM AUTHOR]

Due to the prominent role of recommender systems in our daily lives, it is increasingly important to inform users why certain items are recommended and personalize these explanations to the user. In this study, we explored how explanations in a music recommender system should be designed to fit the preference of different personal characteristics. More specifically, we investigated three personal characteristics that influence the perception of explanations in music recommender system interfaces: need for cognition, musical sophistication, and openness. For each of these personal characteristics, we designed explanations for users with lower and higher levels of the personal characteristic. Afterward, we conducted for each personal characteristic a within-subject user study in which we compared the two explanations. Based on the results of these user studies, we provide design suggestions to adapt explanations to different levels of these three personal characteristics. In general, we suggest providing explanations up-front for all recommendations at once. For users low in need for cognition, displaying these explanations must be optional. To support users with low musical sophistication, we suggest providing brief explanations that do not require domain knowledge. For users with low openness, we suggest providing explanations with a lower number of explanation elements. [ABSTRACT FROM AUTHOR]

The pervasive use of computer simulations in the sciences brings novel epistemological issues discussed in the philosophy of science literature since about a decade. Evolutionary biology strongly relies on such simulations, and in relation to it there exists a research program (Artificial Life) that mainly studies simulations themselves. This paper addresses the specificity of computer simulations in evolutionary biology, in the context (described in Sect. 1) of a set of questions about their scope as explanations, the nature of validation processes and the relation between simulations and true experiments or mathematical models. After making distinctions, especially between a weak use where simulations test hypotheses about the world, and a strong use where they allow one to explore sets of evolutionary dynamics not necessarily extant in our world, I argue in Sect. 2 that (weak) simulations are likely to represent in virtue of the fact that they instantiate specific features of causal processes that may be isomorphic to features of some causal processes in the world, though the latter are always intertwined with a myriad of different processes and hence unlikely to be directly manipulated and studied. I therefore argue that these simulations are merely able to provide candidate explanations for real patterns. Section 3 ends up by placing strong and weak simulations in Levins' triangle, that conceives of simulations as devices trying to fulfil one or two among three incompatible epistemic values (precision, realism, genericity). [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

When seeking to explain social regularities (such as gender differences in the labor market) people often rely on internal features of the targets, frequently neglecting structural and systemic factors external to the targets. For example, people might think women leave the job market after childbirth because they are less competent or are better suited for child‐rearing than men, thereby eliding socio‐cultural and economic factors that disadvantage women. Across two studies (total N = 192) we probe 4‐ and 5‐year‐olds and 7‐ and 8‐year‐olds' internal versus structural reasoning about gender. We explore the evaluative and behavioral implications of this reasoning process with both novel gendered behaviors that were experimentally created and familiar gendered behaviors that exist outside of a lab context. We show that children generate more structural explanations, evaluate the structural explanation more positively, expect behaviors to be more mutable, and evaluate gender non‐conforming behaviors more positively when structural cues are provided. However, we also show that such information may be of limited effectiveness at reducing pre‐existing group‐based discriminatory behaviors: children continue to report less willingness to affiliate with peers who display non‐conforming behaviors even in the presence of structural cues. Taken together, these results provide evidence concerning children's structural reasoning about gender categories and shed new light on how such reasoning might affect social evaluations and behavioral intentions. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Abstract: In decision-making problems under uncertainty, a decision table consists of a set of attributes indicating what is the optimal decision (response) within the different scenarios defined by the attributes. We recently introduced a method to give explanations of these responses. In this paper, the method is extended. To do this, it is combined with a query system to answer expert questions about the preferred action for a given instantiation of decision table attributes. The main difficulty is to accurately answer queries associated with incomplete instantiations. Incomplete instantiations are the result of the evaluation of a partial model outputting decision tables that only include a subset of the whole problem, leading to uncertain responses. Our proposal establishes an automatic and interactive dialogue between the decision-support system and the expert to elicit information from the expert to reduce uncertainty. Typically, the process involves learning a Bayesian network structure from a relevant part of the decision table and computing some interesting conditional probabilities that are revised accordingly. [ABSTRACT FROM AUTHOR]

Abstract: 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. [Copyright &y& Elsevier]

Abstract: In this paper, we describe scalable highly expressive reasoner (SHER), a breakthrough technology that provides semantic querying of large relational datasets using OWL ontologies. SHER relies on a unique algorithm based on ontology summarization and combines a traditional in-memory description logic reasoner with a database backed RDF Store to scale reasoning to very large Aboxes. In our latest experiments, SHER is able to do sound and complete conjunctive query answering up to 7 million triples in seconds, and scales to datasets with 60 million triples, responding to queries in minutes. We describe the SHER system architecture, discuss the underlying components and their functionality, and briefly highlight two concrete use-cases of scalable OWL reasoning based on SHER in the Health Care and Life Science space. The SHER system, with the source code, is available for download (free for academic use) at: http://www.alphaworks.ibm.com/tech/sher. [Copyright &y& Elsevier]

Abstract: Network security tests should be periodically conducted to detect vulnerabilities before they are exploited. However, analysis of testing results is resource intensive with many data and requires expertise because it is an unsupervised domain. This paper presents how to automate and improve this analysis through the identification and explanation of device groups with similar vulnerabilities. Clustering is used for discovering hidden patterns and abnormal behaviors. Self-organizing maps are preferred due to their soft computing capabilities. Explanations based on anti-unification give comprehensive descriptions of clustering results to analysts. This approach is integrated in Consensus, a computer-aided system to detect network vulnerabilities. [Copyright &y& Elsevier]

Abstract: The goal of predictive toxicology is the automatic construction of carcinogenecity models. Most common artificial intelligence techniques used to construct these models are inductive learning methods. In a previous work we presented an approach that uses lazy learning methods for solving the problem of predicting carcinogenecity. Lazy learning methods solve new problems based on their similarity to already solved problems. Nevertheless, a weakness of these kind of methods is that sometimes the result is not completely understandable by the user. In this paper we propose an explanation scheme for a concrete lazy learning method. This scheme is particularly interesting to justify the predictions about the carcinogenesis of chemical compounds. In addition we propose that these explanations could be used to build a partial domain knowledge. In our particular case, we use the explanations for building general knowledge about carcinogenesis. [Copyright &y& Elsevier]

Abstract: This paper describes an explanation-based tools for constraint programming system. These tools provide to the user the conflicts when it raise during solving process. Our tools simulate constraint additions and/or constraint relaxations without any propagation; it also determine if a given constraint belongs to a conflict and it provide diagnosis tool (e.g. why variable cannot take value val?). With more user-friendly representation of conflicts and explanations, our proposed tools give better problem understanding to the user. We prooved that the proposed tools are efficient, and while there is no debugging system that allow the user to interact with the solver, our explanation-based tools could be used for many other applications. [Copyright &y& Elsevier]