{"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/bertopic-neural-topic-modeling-with-a-class","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","arxiv_id":"2203.05794","date":"2022-03-11","proceeding":null,"authors":["Maarten Grootendorst"],"abstract":"Topic models can be useful tools to discover latent topics in collections of documents. Recent studies have shown the feasibility of approach topic modeling as a clustering task. We present BERTopic, a topic model that extends this process by extracting coherent topic representation through the development of a class-based variation of TF-IDF. More specifically, BERTopic generates document embedding with pre-trained transformer-based language models, clusters these embeddings, and finally, generates topic representations with the class-based TF-IDF procedure. BERTopic generates coherent topics and remains competitive across a variety of benchmarks involving classical models and those that follow the more recent clustering approach of topic modeling.","url_abs":"https://arxiv.org/abs/2203.05794v1","url_pdf":"https://arxiv.org/pdf/2203.05794v1.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":"bertopic-neural-topic-modeling-with-a-class","repo_url":"https://github.com/MaartenGr/BERTopic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bertopic-neural-topic-modeling-with-a-class","repo_url":"https://github.com/maartengr/bertopic_evaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"bertopic-neural-topic-modeling-with-a-class","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":"clustering","task_name":"Clustering"},{"task_slug":"document-embedding","task_name":"Document Embedding"},{"task_slug":"topic-models","task_name":"Topic Models"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"contextualized-topic-models","method_name":"Contextualized Topic Models"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.05794","atlas_url":"https://app.syntology.ai/?focus=2203.05794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05794"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maartengr/bertopic_evaluation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaartenGr/BERTopic","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/johntailor/bertsenclu","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"repositories":2},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"15fd8763d297a3dd","entry":"get_unique_distances","repo":"MaartenGr/BERTopic","repo_kind":"official","path":"bertopic/_utils.py","file_url":"https://github.com/MaartenGr/BERTopic/blob/HEAD/bertopic/_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15fd8763d297a3dd"}},{"code_sha256_prefix":"bb9b6185ffed9e10","entry":"highlight_max","repo":"maartengr/bertopic_evaluation","repo_kind":"official","path":"evaluation/results.py","file_url":"https://github.com/maartengr/bertopic_evaluation/blob/HEAD/evaluation/results.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb9b6185ffed9e10"}},{"code_sha256_prefix":"6076b61f860ad3f7","entry":"parse_args","repo":"johntailor/bertsenclu","repo_kind":"listed","path":"visual.py","file_url":"https://github.com/johntailor/bertsenclu/blob/HEAD/visual.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6076b61f860ad3f7"}},{"code_sha256_prefix":"35fc50f41b12a40e","entry":"select_topic_representation","repo":"MaartenGr/BERTopic","repo_kind":"official","path":"bertopic/_utils.py","file_url":"https://github.com/MaartenGr/BERTopic/blob/HEAD/bertopic/_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35fc50f41b12a40e"}},{"code_sha256_prefix":"ff6563e35a9dec05","entry":"validate_distance_matrix","repo":"MaartenGr/BERTopic","repo_kind":"official","path":"bertopic/_utils.py","file_url":"https://github.com/MaartenGr/BERTopic/blob/HEAD/bertopic/_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff6563e35a9dec05"}},{"code_sha256_prefix":"38254e980569b45b","entry":"load_files_from_hf","repo":"MaartenGr/BERTopic","repo_kind":"official","path":"bertopic/_save_utils.py","file_url":"https://github.com/MaartenGr/BERTopic/blob/HEAD/bertopic/_save_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38254e980569b45b"}},{"code_sha256_prefix":"7c653278b4e162d2","entry":"load_local_files","repo":"MaartenGr/BERTopic","repo_kind":"official","path":"bertopic/_save_utils.py","file_url":"https://github.com/MaartenGr/BERTopic/blob/HEAD/bertopic/_save_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c653278b4e162d2"}},{"code_sha256_prefix":"3bd90f9729c9eb39","entry":"push_to_hf_hub","repo":"MaartenGr/BERTopic","repo_kind":"official","path":"bertopic/_save_utils.py","file_url":"https://github.com/MaartenGr/BERTopic/blob/HEAD/bertopic/_save_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bd90f9729c9eb39"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}