Search

Neuropsychiatric disorders affect the lives of individuals from cognitive, emotional, and behavioral aspects, impact the quality of their lives, and even lead to death. Outside the medical area, these diseases have also started to be the subject of investigation in the field of Artificial Intelligence: especially Natural Language Processing (NLP) and Computer Vision. The usage of NLP techniques to understand medical symptoms eases the process of identifying and learning more about language-related aspects of neuropsychiatric conditions, leading to better diagnosis and treatment options. This survey shows the evolution of the detection of linguistic markers specific to a series of neuropsychiatric disorders and symptoms. For each disease or symptom, the article presents a medical description, specific linguistic markers, the results obtained using markers, and datasets. Furthermore, this paper offers a critical analysis of the work undertaken to date and suggests potential directions for future research in the field. [ABSTRACT FROM AUTHOR]

In this paper, a new method that computes the aesthetics of a melody fragment is proposed, starting from dissonances. While music generated with artificial intelligence applications may be produced considerably more quickly than human-composed music, it has the drawback of not being appreciated like a human composition, being many times perceived by humans as artificial. For achieving supervised machine learning objectives of improving the quality of the great number of generated melodies, it is a challenge to ask humans to grade them. Therefore, it would be preferable if the aesthetics of artificial-intelligence-generated music is calculated by an algorithm. The proposed method in this paper is based on a neural network and a mathematical formula, which has been developed with the help of a study in which 108 students evaluated the aesthetics of several melodies. For evaluation, numerical values generated by this method were compared with ratings provided by human listeners from a second study in which 30 students participated and scores were generated by an existing different method developed by psychologists and three other methods developed by musicians. Our method achieved a Pearson correlation of 0.49 with human aesthetic scores, which is a much better result than other methods obtained. Additionally, our method made a distinction between human-composed melodies and artificial-intelligence-generated scores in the same way that human listeners did. [ABSTRACT FROM AUTHOR]

This paper proposes a supervised machine learning system to detect fake news in online sources published in Romanian. Additionally, this work presents a comparison of the obtained results by using recurrent neural networks based on long short-term memory and gated recurrent unit cells, a convolutional neural network, and a Bidirectional Encoder Representations from Transformers (BERT) model, namely RoBERT, a pre-trained Romanian BERT model. The deep learning architectures are compared with the results achieved by two classical classification algorithms: Naïve Bayes and Support Vector Machine. The proposed approach is based on a Romanian news corpus containing 25,841 true news items and 13,064 fake news items. The best result is over 98.20%, achieved by the convolutional neural network, which outperforms the standard classification methods and the BERT models. Moreover, based on irony detection and sentiment analysis systems, additional details are revealed about the irony phenomenon and sentiment analysis field which are used to tackle fake news challenges. [ABSTRACT FROM AUTHOR]

The paper analyzes if it is possible to grow an I-Thou relation in the sense of Martin Buber with an artificial, conversational agent developed with Natural Language Processing techniques. The requirements for such an agent, the possible approaches for the implementation, and their limitations are discussed. The relation of the achievement of this goal with the Turing test is emphasized. Novel perspectives on the I-Thou and I-It relations are introduced according to the sociocultural paradigm and Mikhail Bakhtin's dialogism, polyphony inter-animation, and carnavalesque. The polyphonic model, the associated analysis method, and the support tools are introduced. Some ideas on how the polyphonic model may be used for the implementation of a computer application able to analyze some features of the existence of an I-Thou relation are included. [ABSTRACT FROM AUTHOR]

The broad use of computer-supported collaborative-learning (CSCL) environments (e.g., instant messenger-chats, forums, blogs in online communities, and massive open online courses) calls for automated tools to support tutors in the time-consuming process of analyzing collaborative conversations. In this article, the authors propose and validate the cohesion network analysis (CNA) model, housed within the ReaderBench platform. CNA, grounded in theories of cohesion, dialogism, and polyphony, is similar to social network analysis (SNA), but it also considers text content and discourse structure and, uniquely, uses automated cohesion indices to generate the underlying discourse representation. Thus, CNA enhances the power of SNA by explicitly considering semantic cohesion while modeling interactions between participants. The primary purpose of this article is to describe CNA analysis and to provide a proof of concept, by using ten chat conversations in which multiple participants debated the advantages of CSCL technologies. Each participant’s contributions were human-scored on the basis of their relevance in terms of covering the central concepts of the conversation. SNA metrics, applied to the CNA sociogram, were then used to assess the quality of each member’s degree of participation. The results revealed that the CNA indices were strongly correlated to the human evaluations of the conversations. Furthermore, a stepwise regression analysis indicated that the CNA indices collectively predicted 54% of the variance in the human ratings of participation. The results provide promising support for the use of automated computational assessments of collaborative participation and of individuals’ degrees of active involvement in CSCL environments. [ABSTRACT FROM AUTHOR]

Abstract Informal learning in online knowledge building communities (OKBCs) often starts with online academic help seeking, and with visitor inquiries on specific topics. In such a context, learning presupposes adequate OKBC response. Employing a social learning analytics approach based on natural language processing and Bakhtin's theory of dialogism, this study aims to predict blogger OKBC response. Manipulating the blog topic (well-defined vs. ill-defined) and the visitor inquiry format (off-topic vs. on-topic), a field experiment with a 2 × 2 factorial design was conducted on a sample of N = 68 blogger communities with a total of 25,303 members. For the entire sample, the community response was influenced only by the inquiry format. In a separate examination of the experimental groups, however, this remained true only for the well-defined topic, whereas for the ill-defined topic the community response only depended on the previously established dialog quality. The findings suggest identification criteria for responsive communities, which can support newcomer integration in OKBCs and, from a larger perspective, the use of OKBCs as components of formal learning environments. Highlights • We examined collaborative dialog in online knowledge building communities. • Community response is an essential prerequisite of informal learning. • Automated dialog analysis based on Bakhtin's dialogism was employed. • For all and well-defined topics, only inquiry format influenced community response. • For ill-defined topics only dialog quality influenced community response. [ABSTRACT FROM AUTHOR]

This paper presents a methodology for applying automated essay scoring in educational settings. The methodology was tested and validated on a dataset of 173 reports (in Dutch language) that students have created in an applied game on environmental policy. Natural Language Processing technologies from the ReaderBench framework were used to generate an extensive set of textual complexity indices for each of the reports. Afterwards, different machine learning algorithms were used to predict the scores. By combining binary classification (pass or fail) and a probabilistic model for Precision, a trade-off can be made between validity of automated score prediction (Precision) and the reduction of teacher workload required for manual assessment. It was found from the sample that substantial workload reduction can be achieved, while preserving high precision: allowing for a precision of 95% or higher would already reduce the teacher's workload to 74%; lowering precision to 80% produces a workload reduction of 50%. [ABSTRACT FROM AUTHOR]

Disinformation currently floods the Internet worldwide and likely affects social knowledge building in online communities. Strategic framing in the form of emotional, value, and semantic framing is a common tool fake news producers use to more efficiently disseminate their content, yet these strategies have not been sufficiently examined, even less in relationship with the online dialog initiated by misinformation. In this exploratory study we aim to investigate the most relevant types of strategic framing and their role as predictors of news consumers' emotions, argumentation, and social knowledge building in the online dialog on a German alternative news site. Employing both manual and automated content analysis, we found significant relationships between framing in posted news articles and the subsequent online dialog. News framing predicted negative emotions in the online discussions and interfered with argumentation and social knowledge building. Conclusions pertain to digital information literacy interventions and further research on news framing. • This study combines framing theory and dialogism with disinformation content. • We utilized both manual and automatic content analysis to discover prominent frames in fake news content. • We analyzed roughly 1500 comments from a German fake news site. • Framing predicted social knowledge building in the sense of dialogism and might have led to an echo chamber environment. [ABSTRACT FROM AUTHOR]

Computer-Supported Collaborative Learning tools are exhibiting an increased popularity in education, as they allow multiple participants to easily communicate, share knowledge, solve problems collaboratively, or seek advice. Nevertheless, multi-participant conversation logs are often hard to follow by teachers due to the mixture of multiple and many times concurrent discussion threads, with different interaction patterns between participants. Automated guidance can be provided with the help of Natural Language Processing techniques that target the identification of topic mixtures and of semantic links between utterances in order to adequately observe the debate and continuation of ideas. This paper introduces a method for discovering such semantic links embedded within chat conversations using string kernels, word embeddings, and neural networks. Our approach was validated on two datasets and obtained state-of-the-art results on both. Trained on a relatively small set of conversations, our models relying on string kernels are very effective for detecting such semantic links with a matching accuracy larger than 50% and represent a better alternative to complex deep neural networks, frequently employed in various Natural Language Processing tasks where large datasets are available. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has changed the entire world, while the impact and usage of online learning environments has greatly increased. This paper presents a new version of the ReaderBench framework, grounded in Cohesion Network Analysis, which can be used to evaluate the online activity of students as a plug-in feature to Moodle. A Recurrent Neural Network with LSTM cells that combines global features, including participation and initiation indices, with a time series analysis on timeframes is used to predict student grades, while multiple sociograms are generated to observe interaction patterns. Students' behaviors and interactions are compared before and during COVID-19 using two consecutive yearly instances of an undergraduate course in Algorithm Design, conducted in Romanian using Moodle. The COVID-19 outbreak generated an off-balance, a drastic increase in participation, followed by a decrease towards the end of the semester, compared to the academic year 2018–2019 when lower fluctuations in participation were observed. The prediction model for the 2018–2019 academic year obtained an R 2 of 0.27, while the model for the second year obtained a better R 2 of 0.34, a value arguably attributable to an increased volume of online activity. Moreover, the best model from the first academic year is partially generalizable to the second year, but explains a considerably lower variance (R 2 = 0.13). In addition to the quantitative analysis, a qualitative analysis of changes in student behaviors using comparative sociograms further supported conclusions that there were drastic changes in student behaviors observed as a function of the COVID-19 pandemic. • We evaluate students' behaviors before and during COVID-19 as a plug-in to Moodle. • A RNN combines global features with time series analysis to predict student grades. • Multiple sociograms are generated to observe interaction patterns. • A significant increase in online participation is observed during the pandemic. • The prediction model obtained an R 2 of 0.27 and 0.34 for the two academic years. [ABSTRACT FROM AUTHOR]

Using online learning communities (OLCs) from the Internet as informal learning environments raises the question how likely these communities will integrate learners as new members, i.e., how integrative these OLCs will be. Such prediction is the purpose of the current study. To achieve this, an identification method of the central, intermediate, and peripheral OLC layers is proposed. Based on the CSCL approaches of voices interanimation and polyphony, an advanced natural language processing framework was employed for dialog analysis in N = 20 integrative vs. non-integrative blog-based OLCs involving 2342 users over one year. Hierarchical clusters built upon communicative centrality reflect socio-cognitive structures including central, intermediate, and peripheral OLC members. The resulting clusters were assigned to the central, intermediate and peripheral community layers with 55–100% consistency, whereas most consistent identification criterion of the socio-cognitive OLC structures was the outdegree centrality, followed by the blog owner inclusion, the numbers of participants, eccentricity and indegree centrality. Subsequently, OLC integrativity was predicted with up to 90% accuracy based on topic complexity, socio-cognitive structure, and automatically assessed dialog characteristics. Consequences for further research and educational practice are discussed. • Using online learning communities for learning is a matter of integrativity. • We predicted integrativity, i.e., how likely online communites integrate newcomers. • The prediction was based on automated dialog analysis in blogger communities. • We analyzed N = 20 blogger communities involving 2342 users. • We reached 90% prediction accuracy based on text complexity and other indicators. [ABSTRACT FROM AUTHOR]