{"doi":"10.3115/1557690.1557709","title":"Blog categorization exploiting domain dictionary and dynamically estimated domains of unknown words","abstract":null,"journal":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies Short Papers - HLT '08","year":2008,"id":682517,"datarank":0.32958368660043297,"base_score":2.1972245773362196,"endowment":2.1972245773362196,"self_citation_contribution":0.32958368660043297,"citation_network_contribution":0.0,"self_endowment_contribution":0.32958368660043297,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":8,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1752909,"name":"Sadao Kurohashi","orcid":null,"position":1,"is_corresponding":false},{"id":1783056,"name":"Chikara Hashimoto","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Blog categorization exploiting domain dictionary and dynamically estimated domains of unknown words","abstract":"This paper presents an approach to text categorization that i) uses no machine learning and ii) reacts on-the-fly to unknown words. These features are important for categorizing Blog articles, which are updated on a daily basis and filled with newly coined words. We categorize 600 Blog articles into 12 domains. As a result, our categorization method achieved an accuracy of 94.0% (564/600).","is_dataset_classified":null,"base_score":2.1972245773362196,"endowment":2.1972245773362196,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"21097893","pmcid":null,"openalex_id":"https://openalex.org/W2133651098","authors":[],"funders":[],"total_grants":0,"fwci":0.7554,"citation_percentile":0.70227247,"influential_citations":0,"citation_trend":[{"year":2012,"count":1},{"year":2013,"count":1},{"year":2014,"count":3}],"oa_status":"gold","license":null,"oa_locations":[{"url":"https://dl.acm.org/doi/pdf/10.5555/1557690.1557709","host_type":""},{"url":"https://dl.acm.org/doi/pdf/10.5555/1557690.1557709","host_type":"GOLD"},{"url":"https://dl.acm.org/doi/pdf/10.5555/1557690.1557709","host_type":""},{"url":"https://doi.org/10.3115/1557690.1557709","host_type":""},{"url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.7219","host_type":""}],"fields_of_study":["Text and Document Classification Technologies","Web Data Mining and Analysis","Spam and Phishing Detection","Computer Science"],"mesh_terms":[],"keywords":["Categorization","Text categorization","Computer science","Domain (mathematical analysis)","Natural language processing","Artificial intelligence","Basis (linear algebra)","Information retrieval","Mathematics"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Quality Education"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-17T20:37:12.933924Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}