Supporting argumentation dialogues in group decision support systems: an approach based on dynamic clustering

• Autor(a) principal: Conceição, Luís
• Data de Publicação: 2022
• Outros Autores: Rodrigues, Vasco, Meira, Jorge, Marreiros, Goreti, Novais, Paulo
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://hdl.handle.net/1822/81033
• topic: Group decision making; Dynamic clustering; Natural language processing; Argumentation; Science & Technology

Group decision support systems (GDSSs) have been widely studied over the recent decades. The Web-based group decision support systems appeared to support the group decision-making process by creating the conditions for it to be effective, allowing the management and participation in the process to be carried out from any place and at any time. In GDSS, argumentation is ideal, since it makes it easier to use justifications and explanations in interactions between decision-makers so they can sustain their opinions. Aspect-based sentiment analysis (ABSA) intends to classify opinions at the aspect level and identify the elements of an opinion. Intelligent reports for GDSS provide decision makers with accurate information about each decision-making round. Applying ABSA techniques to group decision making context results in the automatic identification of alternatives and criteria, for instance. This automatic identification is essential to reduce the time decision makers take to step themselves up on group decision support systems and to offer them various insights and knowledge on the discussion they are participating in. In this work, we propose and implement a methodology that uses an unsupervised technique and clustering to group arguments on topics around a specific alternative, for example, or a discussion comparing two alternatives. We experimented with several combinations of word embedding, dimensionality reduction techniques, and different clustering algorithms to achieve the best approach. The best method consisted of applying the KMeans++ clustering technique, using SBERT as a word embedder with UMAP dimensionality reduction. These experiments achieved a silhouette score of 0.63 with eight clusters on the baseball dataset, which wielded good cluster results based on their manual review and word clouds. We obtained a silhouette score of 0.59 with 16 clusters on the car brand dataset, which we used as an approach validation dataset. With the results of this work, intelligent reports for GDSS become even more helpful, since they can dynamically organize the conversations taking place by grouping them on the arguments used.