{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/topic-modeling-based-on-keywords-and-context","title":"Topic Modeling based on Keywords and Context","arxiv_id":"1710.02650","date":"2017-10-07","proceeding":null,"authors":["Johannes Schneider"],"abstract":"Current topic models often suffer from discovering topics not matching human\nintuition, unnatural switching of topics within documents and high\ncomputational demands. We address these concerns by proposing a topic model and\nan inference algorithm based on automatically identifying characteristic\nkeywords for topics. Keywords influence topic-assignments of nearby words. Our\nalgorithm learns (key)word-topic scores and it self-regulates the number of\ntopics. Inference is simple and easily parallelizable. Qualitative analysis\nyields comparable results to state-of-the-art models (eg. LDA), but with\ndifferent strengths and weaknesses. Quantitative analysis using 9 datasets\nshows gains in terms of classification accuracy, PMI score, computational\nperformance and consistency of topic assignments within documents, while most\noften using less topics.","url_abs":"http://arxiv.org/abs/1710.02650v2","url_pdf":"http://arxiv.org/pdf/1710.02650v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"topic-modeling-based-on-keywords-and-context","repo_url":"https://github.com/JohnTailor/tkm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"topic-modeling-based-on-keywords-and-context","repo_url":"https://github.com/johntailor/bertsenclu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"topic-models","task_name":"Topic Models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}