Matches in SemOpenAlex for { <https://semopenalex.org/work/W2125846172> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2125846172 abstract "Both sentiment analysis and topic classification are frequently used in customer care and marketing. They can help people understand the brand perception and customer opinions from social media, such as online posts, tweets, forums, and blogs. As such, in recent years, many solutions have been proposed for both tasks. However, we believe that the following two problems have not been addressed adequately: (1) Conventional solutions usually treat the two tasks in isolation. When the two tasks are closely related (e.g., posts about customer care often have a negative tone), exploring their correlation may yield a better accuracy; (2) Each post is usually assigned with only one sentiment label and one topic label. Since social media is, compared to traditional document corpus, more noisy, ambiguous, and sparser, single label classification may not be able to capture the post classes accurately. To address these two problems, in this paper, we propose a multi-task multi-label (MTML) classification model that performs classification of both sentiments and topics concurrently. It incorporates results of each task from prior steps to promote and reinforce the other iteratively. For each task, the model is trained with multiple labels so that they can help address class ambiguity. In the empirical validation, we compare the accuracy of MTML model against four competing methods in two different settings. Results show that MTML produces a much higher accuracy of both sentiment and topic classifications." @default.
- W2125846172 created "2016-06-24" @default.
- W2125846172 creator A5011510592 @default.
- W2125846172 creator A5017487986 @default.
- W2125846172 creator A5019479187 @default.
- W2125846172 creator A5042838912 @default.
- W2125846172 date "2013-05-02" @default.
- W2125846172 modified "2023-10-03" @default.
- W2125846172 title "Sentiment and topic analysis on social media" @default.
- W2125846172 cites W1550946299 @default.
- W2125846172 cites W1967849786 @default.
- W2125846172 cites W2027549957 @default.
- W2125846172 cites W2027869746 @default.
- W2125846172 cites W2049101093 @default.
- W2125846172 cites W2089204874 @default.
- W2125846172 cites W2102630986 @default.
- W2125846172 cites W2137349054 @default.
- W2125846172 cites W2143104527 @default.
- W2125846172 cites W2143570397 @default.
- W2125846172 cites W2144752499 @default.
- W2125846172 cites W2146241755 @default.
- W2125846172 cites W2170414372 @default.
- W2125846172 cites W2913340405 @default.
- W2125846172 doi "https://doi.org/10.1145/2464464.2464512" @default.
- W2125846172 hasPublicationYear "2013" @default.
- W2125846172 type Work @default.
- W2125846172 sameAs 2125846172 @default.
- W2125846172 citedByCount "26" @default.
- W2125846172 countsByYear W21258461722013 @default.
- W2125846172 countsByYear W21258461722014 @default.
- W2125846172 countsByYear W21258461722015 @default.
- W2125846172 countsByYear W21258461722016 @default.
- W2125846172 countsByYear W21258461722017 @default.
- W2125846172 countsByYear W21258461722018 @default.
- W2125846172 countsByYear W21258461722019 @default.
- W2125846172 countsByYear W21258461722020 @default.
- W2125846172 countsByYear W21258461722021 @default.
- W2125846172 countsByYear W21258461722022 @default.
- W2125846172 crossrefType "proceedings-article" @default.
- W2125846172 hasAuthorship W2125846172A5011510592 @default.
- W2125846172 hasAuthorship W2125846172A5017487986 @default.
- W2125846172 hasAuthorship W2125846172A5019479187 @default.
- W2125846172 hasAuthorship W2125846172A5042838912 @default.
- W2125846172 hasConcept C119857082 @default.
- W2125846172 hasConcept C136764020 @default.
- W2125846172 hasConcept C154945302 @default.
- W2125846172 hasConcept C162324750 @default.
- W2125846172 hasConcept C187736073 @default.
- W2125846172 hasConcept C199360897 @default.
- W2125846172 hasConcept C204321447 @default.
- W2125846172 hasConcept C23123220 @default.
- W2125846172 hasConcept C2777212361 @default.
- W2125846172 hasConcept C2780451532 @default.
- W2125846172 hasConcept C2780522230 @default.
- W2125846172 hasConcept C41008148 @default.
- W2125846172 hasConcept C518677369 @default.
- W2125846172 hasConcept C66402592 @default.
- W2125846172 hasConceptScore W2125846172C119857082 @default.
- W2125846172 hasConceptScore W2125846172C136764020 @default.
- W2125846172 hasConceptScore W2125846172C154945302 @default.
- W2125846172 hasConceptScore W2125846172C162324750 @default.
- W2125846172 hasConceptScore W2125846172C187736073 @default.
- W2125846172 hasConceptScore W2125846172C199360897 @default.
- W2125846172 hasConceptScore W2125846172C204321447 @default.
- W2125846172 hasConceptScore W2125846172C23123220 @default.
- W2125846172 hasConceptScore W2125846172C2777212361 @default.
- W2125846172 hasConceptScore W2125846172C2780451532 @default.
- W2125846172 hasConceptScore W2125846172C2780522230 @default.
- W2125846172 hasConceptScore W2125846172C41008148 @default.
- W2125846172 hasConceptScore W2125846172C518677369 @default.
- W2125846172 hasConceptScore W2125846172C66402592 @default.
- W2125846172 hasLocation W21258461721 @default.
- W2125846172 hasOpenAccess W2125846172 @default.
- W2125846172 hasPrimaryLocation W21258461721 @default.
- W2125846172 hasRelatedWork W2024691726 @default.
- W2125846172 hasRelatedWork W2326619756 @default.
- W2125846172 hasRelatedWork W2389073147 @default.
- W2125846172 hasRelatedWork W2748952813 @default.
- W2125846172 hasRelatedWork W2961085424 @default.
- W2125846172 hasRelatedWork W3192794374 @default.
- W2125846172 hasRelatedWork W4306674287 @default.
- W2125846172 hasRelatedWork W4362613237 @default.
- W2125846172 hasRelatedWork W4379932966 @default.
- W2125846172 hasRelatedWork W4224009465 @default.
- W2125846172 isParatext "false" @default.
- W2125846172 isRetracted "false" @default.
- W2125846172 magId "2125846172" @default.
- W2125846172 workType "article" @default.