Seeded Sequential LDA: A Semi-Supervised Algorithm for Topic-Specific Analysis of Sentences
Kohei Watanabe, Alexander Baturo · Social Science Computer Review · 2023
Topic models have been widely used by researchers across disciplines to automatically analyze large textual data. However, they often fail to automate content analysis, because the algorithms cannot accurately classify individual sentences into pre-defined topics. Aiming to make topic classification more theoretically grounded and content analysis in general more topic-specific, we have developed Seeded Sequential Latent Dirichlet allocation (LDA), extending the existing LDA algorithm, and implementing it in a widely accessible open-source package. Taking a large corpus of speeches delivered by delegates at the United Nations General Assembly as an example, we explain how our algorithm differs from the original algorithm; why it can classify sentences more accurately; how it accepts pre-defined topics in deductive or semi-deductive analysis; how such ex-ante topic mapping differs from ex-post topic mapping; how it enables topic-specific framing analysis in applied research. We also offer practical guidance on how to determine the optimal number of topics and select seed words for the algorithm.
Cited by 64 works. doi:10.1177/08944393231178605 Open-access PDF
Authors
References
- Finding scientific topics
- Dynamic topic models
- Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts
- Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing
- Parameter estimation for text analysis
- A biterm topic model for short texts
- quanteda: An R package for the quantitative analysis of textual data
- A density-based method for adaptive LDA model selection
- On Finding the Natural Number of Topics with Latent Dirichlet Allocation: Some Observations
- Affective News: The Automated Coding of Sentiment in Political Texts