The following two papers were accepted for the workshop:
Abstract. We present an approach for employing KR methods sequentially and evaluating them according to their predictive power for human reasoning. The approach uses epistemic spaces and allows the injection of cognitive aspects into the approach. We report two instantiations of the general approach in which the epistemic states are ranking functions. The first is based on belief merging, and the second instantiation is based on belief revision. Both instantiations also use cognitively inspired formal approaches to construct meaningful internal representations. We also report the evaluation of these instantiations on an experimental dataset about human reasoning. The results suggest that KR approaches may benefit from augmentation with cognitively inspired processes.
Abstract. Recently, there has been a growing trend in studies that employ ontology-based methods to analyze sentiment in social media comments in Vietnam. Ontology, a model comprising concepts, attributes, and relationships, serves as a knowledge reference framework for expressing emotions in comments. This approach enhances understanding of how Vietnamese individuals convey emotions on platforms such as YouTube, Facebook, and others. In contrast to traditional sentiment analysis methods, ontology aims to achieve more detailed and accurate sentiment analysis by leveraging semantic connections between concepts. Therefore, this paper proposes: (1) employing ontology for sentiment analysis in Vietnamese social media, (2) collecting and preprocessing comment data from popular platforms in Vietnam, (3) utilizing ontology to assign sentiment labels (positive, negative) to comments, (4) analyzing sentiment patterns and trends in comments, and (5) evaluating the performance of ontology-based methods versus traditional sentiment analysis. The findings of this study contribute to advancing social data analysis techniques and oer insights into user behaviors on Vietnamese social media platforms. Experiments also show that the proposed method achieves the best performance compared to other methods, with an accuracy of up to 0.8657 and an F1 score of up to 0.9174.