A Query-Driven Topic Model

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1764–1777 August 1–6, 2021. ©2021 Association for Computational Linguistics 1764 A Query-Driven Topic Model Zheng Fang1, Yulan He1,2 and Rob Procter1,2 1Department of Computer Science, University of Warwick 2The Alan Turing Institute, London, UK {Z.Fang.4|Yulan.He|Rob.Procter}@warwick.ac.uk Abstract Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. It has been increasingly widely adopted as a tool in the social sciences, in- cluding political science, digital humanities and sociological research in general. One desirable property of topic models is to al- low users to find topics describing a specific aspect of the corpus. A possible solution is to incorporate domain-specific knowledge into topic modeling, but this requires a spec- ification from domain experts. We propose a novel query-driven topic model that allows users to specify a simple query in words or phrases and return query-related topics, thus avoiding tedious work from domain experts. Our proposed approach is particularly attrac- tive when the user-specified query has a low occurrence in a text corpus, making it difficult for traditional topic models built on word co- occurrence patterns to identify relevant topics. Experimental results demonstrate the effective- ness of our model in comparison with both classical topic models and neural topic mod- els. 1 Introduction Topic modeling aims to infer topics from a collec- tion of documents, where a topic is a salient pattern of the collection and is represented by a distribu- tion over words. The availability in large volume of new sources of unstructured data, such as social media, has presented a challenge to conventional qualitative research methods in the social sciences and humanities and encouraged the exploration of topic modeling as a potential solution (Melville et al., 2019; Hu et al., 2019; Yao and Wang, 2020). In these studies, topic modeling has been applied to questions centered on interpretation and meaning. By analyzing words distribution of topics learnt, researchers can apply inductive reasoning on spe- cific topics and perform a more in-depth study of related documents, allowing them to identify under- lying topical trends and conduct a more thorough analysis of the data. One limitation of conventional topic modeling approaches in these studies is that they can only learn topics from the whole corpus. However, in some cases, researchers may be interested in topics describing specific concepts or aspects of the cor- pus. To identify these topics, researchers have to an- alyze words distribution for all topics, thereby mak- ing it very time consuming. Moreover, it could also happen that the target topics may have a very small presence in the data to be detected directly by a topic model. For instance, given a set of posts about health, researchers may wish specifically to analyze the impact of food on health. If the words related to food have a relatively low frequency of occurrence in the posts, then conventional topic models such as Latent Dirichlet Allocation (LDA) (Blei et al., 2003) may not find any food-related topics …

Content truncated to 500 words