Matches in SemOpenAlex for { <https://semopenalex.org/work/W2807662642> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2807662642 endingPage "1358" @default.
- W2807662642 startingPage "1345" @default.
- W2807662642 abstract "Topic models often produce unexplainable topics that are filled with noisy words. The reason is that words in topic modeling have equal weights. High frequency words dominate the top topic word lists, but most of them are meaningless words, e.g., domain-specific stopwords. To address this issue, in this paper we aim to investigate how to weight words, and then develop a straightforward but effective term weighting scheme, namely entropy weighting (EW). The proposed EW scheme is based on conditional entropy measured by word co-occurrences. Compared with existing term weighting schemes, the highlight of EW is that it can automatically reward informative words. For more robust word weight, we further suggest a combination form of EW (CEW) with two existing weighting schemes. Basically, our CEW assigns meaningless words lower weights and informative words higher weights, leading to more coherent topics during topic modeling inference. We apply CEW to Dirichlet multinomial mixture and latent Dirichlet allocation, and evaluate it by topic quality, document clustering and classification tasks on 8 real world data sets. Experimental results show that weighting words can effectively improve the topic modeling performance over both short texts and normal long texts. More importantly, the proposed CEW significantly outperforms the existing term weighting schemes, since it further considers which words are informative." @default.
- W2807662642 created "2018-06-13" @default.
- W2807662642 creator A5021089407 @default.
- W2807662642 creator A5044246694 @default.
- W2807662642 creator A5048031726 @default.
- W2807662642 creator A5074361573 @default.
- W2807662642 creator A5089123257 @default.
- W2807662642 date "2018-11-01" @default.
- W2807662642 modified "2023-10-17" @default.
- W2807662642 title "Exploring coherent topics by topic modeling with term weighting" @default.
- W2807662642 cites W1972969301 @default.
- W2807662642 cites W2001082470 @default.
- W2807662642 cites W2048195127 @default.
- W2807662642 cites W2097089247 @default.
- W2807662642 cites W2125109223 @default.
- W2807662642 cites W2140321362 @default.
- W2807662642 cites W2145766604 @default.
- W2807662642 cites W2151703435 @default.
- W2807662642 cites W2151975921 @default.
- W2807662642 cites W2152593801 @default.
- W2807662642 cites W2174706414 @default.
- W2807662642 cites W2583067118 @default.
- W2807662642 cites W3099640513 @default.
- W2807662642 doi "https://doi.org/10.1016/j.ipm.2018.05.009" @default.
- W2807662642 hasPublicationYear "2018" @default.
- W2807662642 type Work @default.
- W2807662642 sameAs 2807662642 @default.
- W2807662642 citedByCount "33" @default.
- W2807662642 countsByYear W28076626422019 @default.
- W2807662642 countsByYear W28076626422020 @default.
- W2807662642 countsByYear W28076626422021 @default.
- W2807662642 countsByYear W28076626422022 @default.
- W2807662642 countsByYear W28076626422023 @default.
- W2807662642 crossrefType "journal-article" @default.
- W2807662642 hasAuthorship W2807662642A5021089407 @default.
- W2807662642 hasAuthorship W2807662642A5044246694 @default.
- W2807662642 hasAuthorship W2807662642A5048031726 @default.
- W2807662642 hasAuthorship W2807662642A5074361573 @default.
- W2807662642 hasAuthorship W2807662642A5089123257 @default.
- W2807662642 hasConcept C106301342 @default.
- W2807662642 hasConcept C119857082 @default.
- W2807662642 hasConcept C121332964 @default.
- W2807662642 hasConcept C124101348 @default.
- W2807662642 hasConcept C126838900 @default.
- W2807662642 hasConcept C154945302 @default.
- W2807662642 hasConcept C171686336 @default.
- W2807662642 hasConcept C183115368 @default.
- W2807662642 hasConcept C204321447 @default.
- W2807662642 hasConcept C2524010 @default.
- W2807662642 hasConcept C2776214188 @default.
- W2807662642 hasConcept C33923547 @default.
- W2807662642 hasConcept C41008148 @default.
- W2807662642 hasConcept C500882744 @default.
- W2807662642 hasConcept C61797465 @default.
- W2807662642 hasConcept C62520636 @default.
- W2807662642 hasConcept C71924100 @default.
- W2807662642 hasConcept C73555534 @default.
- W2807662642 hasConcept C90805587 @default.
- W2807662642 hasConceptScore W2807662642C106301342 @default.
- W2807662642 hasConceptScore W2807662642C119857082 @default.
- W2807662642 hasConceptScore W2807662642C121332964 @default.
- W2807662642 hasConceptScore W2807662642C124101348 @default.
- W2807662642 hasConceptScore W2807662642C126838900 @default.
- W2807662642 hasConceptScore W2807662642C154945302 @default.
- W2807662642 hasConceptScore W2807662642C171686336 @default.
- W2807662642 hasConceptScore W2807662642C183115368 @default.
- W2807662642 hasConceptScore W2807662642C204321447 @default.
- W2807662642 hasConceptScore W2807662642C2524010 @default.
- W2807662642 hasConceptScore W2807662642C2776214188 @default.
- W2807662642 hasConceptScore W2807662642C33923547 @default.
- W2807662642 hasConceptScore W2807662642C41008148 @default.
- W2807662642 hasConceptScore W2807662642C500882744 @default.
- W2807662642 hasConceptScore W2807662642C61797465 @default.
- W2807662642 hasConceptScore W2807662642C62520636 @default.
- W2807662642 hasConceptScore W2807662642C71924100 @default.
- W2807662642 hasConceptScore W2807662642C73555534 @default.
- W2807662642 hasConceptScore W2807662642C90805587 @default.
- W2807662642 hasFunder F4320321001 @default.
- W2807662642 hasIssue "6" @default.
- W2807662642 hasLocation W28076626421 @default.
- W2807662642 hasOpenAccess W2807662642 @default.
- W2807662642 hasPrimaryLocation W28076626421 @default.
- W2807662642 hasRelatedWork W142374489 @default.
- W2807662642 hasRelatedWork W1860853633 @default.
- W2807662642 hasRelatedWork W2163194442 @default.
- W2807662642 hasRelatedWork W2884815824 @default.
- W2807662642 hasRelatedWork W3031970385 @default.
- W2807662642 hasRelatedWork W3042958706 @default.
- W2807662642 hasRelatedWork W3102628894 @default.
- W2807662642 hasRelatedWork W3204681432 @default.
- W2807662642 hasRelatedWork W4294597112 @default.
- W2807662642 hasRelatedWork W4302211199 @default.
- W2807662642 hasVolume "54" @default.
- W2807662642 isParatext "false" @default.
- W2807662642 isRetracted "false" @default.
- W2807662642 magId "2807662642" @default.
- W2807662642 workType "article" @default.