Entities as Topic Labels: Combining Entity Linking and Labeled LDA to Improve Topic Interpretability and Evaluability

Abstract

Digital humanities scholars strongly need a corpus exploration method that provides topics easier to interpret than standard LDA topic models. To move towards this goal, here we propose a combination of two techniques, called Entity Linking and Labeled LDA. Our method identifies in an ontology a series of descriptive labels for each document in a corpus. Then it generates a specific topic for each label. Having a direct relation between topics and labels makes interpretation easier; using an ontology as background knowledge limits label ambiguity. As our topics are described with a limited number of clear-cut labels, they promote interpretability and support the quantitative evaluation of the obtained results. We illustrate the potential of the approach by applying it to three datasets, namely the transcription of speeches from the European Parliament fifth mandate, the Enron Corpus and the Hillary Clinton Email Dataset. While some of these resources have already been adopted by the natural language processing community, they still hold a large potential for humanities scholars, part of which could be exploited in studies that will adopt the fine-grained exploration method presented in this paper.

Augmenting Large Language Models for Enhanced Interaction with Government Data Repositories

“…These analyses typically draw from sources like press releases, legislative drafts, and electoral campaign literature. Past studies have also investigated the emphasis senators place on topics through press releases [55], themes in party electoral manifestos [56], subjects addressed in EU parliament speeches [57], and the identification of political events from congressional texts and news [58]. Furthermore, research into politicians' perspectives has focused on delineating their policy stands, assessing alignment or divergence among politicians on specific issues during electoral phases [59], and appraising political personas [60].…”

Natural Language Processing for Policymaking

“…Example of previous studies to analyze the topics and prioritization of political bodies include the research on the prioritization each Senator assigns to topics using press releases (Grimmer, 2010b), topics in different parties' electoral manifestos (Glavaš et al, 2017a), topics in EU parliament speeches (Lauscher et al, 2016) and other various types of text (King and Lowe, 2003;Hopkins and King, 2010;Grimmer, 2010a;Roberts et al, 2014), as well as political event detection from congressional text and news .…”