Matches in SemOpenAlex for { <https://semopenalex.org/work/W2368278370> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2368278370 endingPage "78" @default.
- W2368278370 startingPage "65" @default.
- W2368278370 abstract "Opinion lexicons, which are lists of terms labeled by sentiment, are widely used resources to support automatic sentiment analysis of textual passages. However, existing resources of this type exhibit some limitations when applied to social media messages such as tweets (posts in Twitter), because they are unable to capture the diversity of informal expressions commonly found in this type of media. In this article, we present a method that combines information from automatically annotated tweets and existing hand-made opinion lexicons to expand an opinion lexicon in a supervised fashion. The expanded lexicon contains part-of-speech (POS) disambiguated entries with a probability distribution for positive, negative, and neutral polarity classes, similarly to SentiWordNet. To obtain this distribution using machine learning, we propose word-level attributes based on (a) the morphological information conveyed by POS tags and (b) associations between words and the sentiment expressed in the tweets that contain them. We consider tweets with both hard and soft sentiment labels. The sentiment associations are modeled in two different ways: using point-wise-mutual-information semantic orientation (PMI-SO), and using stochastic gradient descent semantic orientation (SGD-SO), which learns a linear relationship between words and sentiment. The training dataset is labeled by a seed lexicon formed by combining multiple hand-annotated lexicons. Our experimental results show that our method outperforms the three-dimensional word-level polarity classification performance obtained by using PMI-SO alone. This is significant because PMI-SO is a state-of-the-art measure for establishing world-level sentiment. Additionally, we show that lexicons created with our method achieve significant improvements over SentiWordNet for classifying tweets into polarity classes, and also outperform SentiStrength in the majority of the experiments." @default.
- W2368278370 created "2016-06-24" @default.
- W2368278370 creator A5047767877 @default.
- W2368278370 creator A5059992863 @default.
- W2368278370 creator A5087785022 @default.
- W2368278370 date "2016-09-01" @default.
- W2368278370 modified "2023-10-14" @default.
- W2368278370 title "Building a Twitter opinion lexicon from automatically-annotated tweets" @default.
- W2368278370 cites W1986165915 @default.
- W2368278370 cites W1987425720 @default.
- W2368278370 cites W1994645462 @default.
- W2368278370 cites W1995219110 @default.
- W2368278370 cites W2040467972 @default.
- W2368278370 cites W2058339786 @default.
- W2368278370 cites W2084046180 @default.
- W2368278370 cites W2113307939 @default.
- W2368278370 cites W2120199131 @default.
- W2368278370 cites W2156413587 @default.
- W2368278370 cites W2158698691 @default.
- W2368278370 cites W2165938099 @default.
- W2368278370 cites W2306941105 @default.
- W2368278370 cites W2486125749 @default.
- W2368278370 doi "https://doi.org/10.1016/j.knosys.2016.05.018" @default.
- W2368278370 hasPublicationYear "2016" @default.
- W2368278370 type Work @default.
- W2368278370 sameAs 2368278370 @default.
- W2368278370 citedByCount "45" @default.
- W2368278370 countsByYear W23682783702016 @default.
- W2368278370 countsByYear W23682783702017 @default.
- W2368278370 countsByYear W23682783702018 @default.
- W2368278370 countsByYear W23682783702019 @default.
- W2368278370 countsByYear W23682783702020 @default.
- W2368278370 countsByYear W23682783702021 @default.
- W2368278370 countsByYear W23682783702022 @default.
- W2368278370 countsByYear W23682783702023 @default.
- W2368278370 crossrefType "journal-article" @default.
- W2368278370 hasAuthorship W2368278370A5047767877 @default.
- W2368278370 hasAuthorship W2368278370A5059992863 @default.
- W2368278370 hasAuthorship W2368278370A5087785022 @default.
- W2368278370 hasBestOaLocation W23682783702 @default.
- W2368278370 hasConcept C136764020 @default.
- W2368278370 hasConcept C138885662 @default.
- W2368278370 hasConcept C154945302 @default.
- W2368278370 hasConcept C16345878 @default.
- W2368278370 hasConcept C204321447 @default.
- W2368278370 hasConcept C23123220 @default.
- W2368278370 hasConcept C2524010 @default.
- W2368278370 hasConcept C2778121359 @default.
- W2368278370 hasConcept C33923547 @default.
- W2368278370 hasConcept C41008148 @default.
- W2368278370 hasConcept C41895202 @default.
- W2368278370 hasConcept C518677369 @default.
- W2368278370 hasConcept C66402592 @default.
- W2368278370 hasConcept C90805587 @default.
- W2368278370 hasConceptScore W2368278370C136764020 @default.
- W2368278370 hasConceptScore W2368278370C138885662 @default.
- W2368278370 hasConceptScore W2368278370C154945302 @default.
- W2368278370 hasConceptScore W2368278370C16345878 @default.
- W2368278370 hasConceptScore W2368278370C204321447 @default.
- W2368278370 hasConceptScore W2368278370C23123220 @default.
- W2368278370 hasConceptScore W2368278370C2524010 @default.
- W2368278370 hasConceptScore W2368278370C2778121359 @default.
- W2368278370 hasConceptScore W2368278370C33923547 @default.
- W2368278370 hasConceptScore W2368278370C41008148 @default.
- W2368278370 hasConceptScore W2368278370C41895202 @default.
- W2368278370 hasConceptScore W2368278370C518677369 @default.
- W2368278370 hasConceptScore W2368278370C66402592 @default.
- W2368278370 hasConceptScore W2368278370C90805587 @default.
- W2368278370 hasLocation W23682783701 @default.
- W2368278370 hasLocation W23682783702 @default.
- W2368278370 hasOpenAccess W2368278370 @default.
- W2368278370 hasPrimaryLocation W23682783701 @default.
- W2368278370 hasRelatedWork W1631585051 @default.
- W2368278370 hasRelatedWork W2150818832 @default.
- W2368278370 hasRelatedWork W2593058442 @default.
- W2368278370 hasRelatedWork W2626568907 @default.
- W2368278370 hasRelatedWork W2888662092 @default.
- W2368278370 hasRelatedWork W2902285665 @default.
- W2368278370 hasRelatedWork W2903394456 @default.
- W2368278370 hasRelatedWork W2975174210 @default.
- W2368278370 hasRelatedWork W4200238620 @default.
- W2368278370 hasRelatedWork W3205826705 @default.
- W2368278370 hasVolume "108" @default.
- W2368278370 isParatext "false" @default.
- W2368278370 isRetracted "false" @default.
- W2368278370 magId "2368278370" @default.
- W2368278370 workType "article" @default.