Mitigando os Limites das Métricas Atuais de Avaliação de Estratégias de Modelagem de Tópicos

Topic Modeling (TM) helps extract and organize information from large amounts of textual data by discovering semantic topics from documents. This master thesis delves into issues of topic quality evaluation, responsible for driving the advances in the TM field by assessing the overall quality of the topic generation process. Since traditional TM metrics capture the quality of topics by strictly evaluating the words that make up the topics, either syntactically (e.g., NPMI, TF-IDF Coherence) or semantically (e.g., WEP), we investigate whether we are approaching the limits of what the current evaluation metrics can assess regarding TM quality. For this, we perform a comprehensive experimental evaluation, considering three widely used datasets (ACM, 20News, and WOS) for which a natural organization of the collection’s documents into semantic classes (topics) does exist. We contrast the quality of topics generated by four traditional and state-of-the-art TM techniques (i.e., LDA, NMF, CluWords, and BERTopic) with each collection’s “natural topic structure”. Our results show that, despite the importance of the current metrics, they could not capture some important idiosyncratic aspects of the TM task, in this case, the capability of the topics to induce a structural organization of the document space into distinct semantic groups. To mitigate such limitations, we propose incorporating metrics commonly used to evaluate clustering algorithms into the TM evaluation process, relying on some commonalities between TM and clustering tasks. Results highlight the effectiveness of clustering metrics in distinguishing the results of TM techniques compared to the datasets’ground truth (class organization). However, adopting additional evaluation metrics implies expanding the analysis space. Thus, as a third contribution, we propose consolidating the various metrics into a unified framework, using Game Theory for decision-making, specifically Multi-Attribute Utility Theory (MAUT). Our experimental results demonstrate that MAUT allows a more precise assessment of TM quality.