FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3018749573> ?p ?o ?g. }

• W3018749573 abstract "Recently, microblogs platforms such as Twitter are becoming popular day byday. People used Twitter for building common ground, sharing informationand sharing opinions on a variety of topics and discussing current issues. Thus,Twitter becomes source of opinions. Therefore understanding the sentiment ofthe opinion is needed.Over the last decades, sentiment analysis (SA) in social media has been oneof the most research areas in Natural Language Processing (NLP). The aim ofsentiment analysis is to automatically identify the polarity of a document, wheremisinterpreting irony and sarcasm is a big challenge. There is a weak boundaryin the meaning between irony, sarcasm and satire, therefore in this thesis onlythe term sarcasm is employed.Sarcasm is a common phenomenon in social media, which is a nuance form oflanguage for expressing the opposite of what is inferred. Sarcasm generallychanges the polarity of an utterance from positive or negative into its opposite.Therefore, identifying sarcasm correctly can enhance the performance of sentimentclassification. Sarcasm analysis is a difficult task not only for the machine,but also for a human, because of the intentional ambiguity. Although sarcasmdetection has an important effect on sentiment, it is usually ignored in socialmedia analysis because sarcasm analysis is too complicated.Several techniques have been used in sarcasm detection such a semi-supervised,detection sarcasm based on intensifiers and exclamation, the impact of lexical and pragmatic factors, contrast between positive and negative situation verbphrases and hashtags based sentiment analysis. In this thesis, two existingworks; sarcasm as a contrast between positive sentiment and negative situationphrases and hashtags based sentiment analysis are extended. For the formertask, the authors of the work have presented a novel bootstrapping algorithmthat automatically learns a list of positive sentiment phrases and negativesituation phrases from sarcastic tweets. The results showed a contrast betweenpositive and negative and they can be used in recognizing sarcastic tweets.However, the work only identified one type of sarcasm tweets (i.e. positive verbphrases followed by negative situation phrases). In additional they did not workon identifying sarcasm when a negative situation phrases is followed by positivesentiment in the separate sentences. Moreover, the intensity of the negativity isnot considered in their work. In addition, the work did not consider hashtagsand sentiment analysis of hashtags. Hashtag is a topic or key words that aremarked with a tweet. Since many of the hashtags contain polarity, detection ofsarcasm at hashtags level will have a positive effect on polarity classification.The later work which is extended in this thesis works based on the hashtagssentiment analysis. The authors identified sarcastic tweets based on the sarcasmindicators and contrast between the sentiment orientation of the tweets andhashtags. Although, the work was primary work at the level of the hashtagssentiment analysis, they did not use systematic approach for identifying sarcasmindicators. Moreover, they worked only based on the contrast between the sentimentorientation of the tweets and hashtags. Since sarcasm utterance containshyperbole and exaggeration and some hashtags are used for emphasizing thetext, identifying based on the contrast between the sentiment of the tweets andhashtags is not sufficient.To address problems, a Sarcasm Detection Model (SDM) is proposed. In theproposed model, three classifiers; SentiStrength Sarcasm Classifier (SSC), SarcasmHashtags Classifier (SHC) and Hashtags-SentiStrength Sarcasm Classifier(HSSC) is used. SSC is worked at the level of the non-hashtags sentimentanalysis, whereas SHC and HSSC at the level of the hashtags sentiment analysis.In the SSC, sarcasm is identified based on the strength level of tweets.Several lexical and pragmatic features such as emoticons, interjections, capitalwords and elongate words are applied in the proposed SentiStrength formula.Sarcasm Hashtags Classifier (SHC) is used to identify sarcastic tweets based onthe Sarcasm Hashtags Indicator (SHI) and Sentiment Hashtags Analysis (SHA).In the classifier (SHC), a bootstrapping algorithm is used to identify SarcasmHashtags Indicator (SHI). SHI contains a list of hashtags that help to identifysarcastic tweets easily. In the proposed model (SDM), if a tweet contains SHI, itwill be labeled as sarcastic tweet; otherwise the Sentiment Hashtags Analysis(SHA) is applied. SHA is worked based on the contrast between sentimentorientation of the tweets and hashtags. In this part, the hashtags are retokenizedthrough preprocessing and the orientation of the hashtags is identified. Next, the orientation of a tweet without hashtags is also identified. The tweet isconsidered as sarcasm hashtags if there is a contrast between the orientation ofthe tweet and hashtags.The HSSC, works based on the strength level of tweets and hashtags. In thisclassifier, the effect of the sentiment of the hashtags for increasing the polarity ofthe tweets is considered.The Sarcasm Detection Model (SDM) has been tested on two datasets whicheach dataset contains 3000 sarcastic and non- sarcastic tweets. All of the tweetswere extracted randomly using the Twitter API. So far, no work has been donein sarcasm detection at the level of hashtags and non-hashtags based sentimentanalysis. So, the novelty of the proposed model (SDM) is in identifying sarcastictweets by analyzing strength of the tweets at the level of the hashtags andnon-hashtags sentiment analysis. The results of the study (0.85% of precision)demonstrates that the SDM is more accurate and effective than the existingworks which was done based on the contrast between positive and negativesituation phrases and hashtags based sentiment analysis." @default.
• W3018749573 created "2020-05-01" @default.
• W3018749573 creator A5016672621 @default.
• W3018749573 date "2016-07-01" @default.
• W3018749573 modified "2023-09-24" @default.
• W3018749573 title "Sarcasm detection model based on tweets’ strength using hashtags and non-hashtags sentiment analysis" @default.
• W3018749573 hasPublicationYear "2016" @default.
• W3018749573 type Work @default.
• W3018749573 sameAs 3018749573 @default.
• W3018749573 citedByCount "0" @default.
• W3018749573 crossrefType "dissertation" @default.
• W3018749573 hasAuthorship W3018749573A5016672621 @default.
• W3018749573 hasConcept C136764020 @default.
• W3018749573 hasConcept C138885662 @default.
• W3018749573 hasConcept C143275388 @default.
• W3018749573 hasConcept C154945302 @default.
• W3018749573 hasConcept C15744967 @default.
• W3018749573 hasConcept C204321447 @default.
• W3018749573 hasConcept C2775852435 @default.
• W3018749573 hasConcept C2776207355 @default.
• W3018749573 hasConcept C2779975665 @default.
• W3018749573 hasConcept C41008148 @default.
• W3018749573 hasConcept C41895202 @default.
• W3018749573 hasConcept C518677369 @default.
• W3018749573 hasConcept C66402592 @default.
• W3018749573 hasConceptScore W3018749573C136764020 @default.
• W3018749573 hasConceptScore W3018749573C138885662 @default.
• W3018749573 hasConceptScore W3018749573C143275388 @default.
• W3018749573 hasConceptScore W3018749573C154945302 @default.
• W3018749573 hasConceptScore W3018749573C15744967 @default.
• W3018749573 hasConceptScore W3018749573C204321447 @default.
• W3018749573 hasConceptScore W3018749573C2775852435 @default.
• W3018749573 hasConceptScore W3018749573C2776207355 @default.
• W3018749573 hasConceptScore W3018749573C2779975665 @default.
• W3018749573 hasConceptScore W3018749573C41008148 @default.
• W3018749573 hasConceptScore W3018749573C41895202 @default.
• W3018749573 hasConceptScore W3018749573C518677369 @default.
• W3018749573 hasConceptScore W3018749573C66402592 @default.
• W3018749573 hasLocation W30187495731 @default.
• W3018749573 hasOpenAccess W3018749573 @default.
• W3018749573 hasPrimaryLocation W30187495731 @default.
• W3018749573 hasRelatedWork W2007734915 @default.
• W3018749573 hasRelatedWork W2114661483 @default.
• W3018749573 hasRelatedWork W2170414372 @default.
• W3018749573 hasRelatedWork W2232443784 @default.
• W3018749573 hasRelatedWork W2250710744 @default.
• W3018749573 hasRelatedWork W2251958472 @default.
• W3018749573 hasRelatedWork W2268623141 @default.
• W3018749573 hasRelatedWork W2294579401 @default.
• W3018749573 hasRelatedWork W2513138008 @default.
• W3018749573 hasRelatedWork W2556753300 @default.
• W3018749573 hasRelatedWork W2793172163 @default.
• W3018749573 hasRelatedWork W2906720631 @default.
• W3018749573 hasRelatedWork W2908196369 @default.
• W3018749573 hasRelatedWork W2912463350 @default.
• W3018749573 hasRelatedWork W2991000581 @default.
• W3018749573 hasRelatedWork W3036280612 @default.
• W3018749573 hasRelatedWork W3037891159 @default.
• W3018749573 hasRelatedWork W3041285871 @default.
• W3018749573 hasRelatedWork W3042560671 @default.
• W3018749573 hasRelatedWork W3133704247 @default.
• W3018749573 isParatext "false" @default.
• W3018749573 isRetracted "false" @default.
• W3018749573 magId "3018749573" @default.
• W3018749573 workType "dissertation" @default.