Vis enkel innførsel

dc.contributor.authorNaseem, Usman
dc.contributor.authorKhan, Shah K.
dc.contributor.authorRazzak, Imran
dc.contributor.authorHameed, Ibrahim A.
dc.date.accessioned2020-06-30T11:06:55Z
dc.date.available2020-06-30T11:06:55Z
dc.date.created2019-12-17T11:07:34Z
dc.date.issued2019
dc.identifier.isbn978-3-030-35288-2
dc.identifier.urihttps://hdl.handle.net/11250/2660055
dc.description.abstractSocial media sentimental analysis is interesting field with the aim to analyze social conservation and determine deeper context as they apply to a topic or theme. However, it is challenging as tweets are unstructured, informal and noisy in nature. Also, it involves natural language complexities like words with same meanings (Polysemy). Most of the existing approaches mainly rely on clean textual data, however Twitter data is quite noisy in real life. Aiming to improve the performance, in this paper, we present hybrid words representation and Bi-directional Long Short Term Memory (BiLSTM) with attention modeling resulting in improvement in tweet quality by not only treating the noise within the textual context but also considers polysemy, semantics, syntax, out of vocabulary (OOV) words as well as words sentiments within a tweet. The proposed model overcomes the current limitations and improves the accuracy for tweets classification as showed by the evaluation of the model performed on real-world airline related datasets.en_US
dc.language.isoengen_US
dc.publisherSpringeren_US
dc.relation.ispartofAI 2019: Advances in Artificial Intelligence: 32nd Australasian Joint Conference, Adelaide, SA, Australia, December 2–5, 2019, Proceedings Editors
dc.relation.urihttps://link.springer.com/chapter/10.1007%2F978-3-030-35288-2_31
dc.titleHybrid Words Representation for Airlines Sentiment Analysisen_US
dc.typeChapteren_US
dc.description.versionpublishedVersionen_US
dc.source.pagenumber381-392en_US
dc.identifier.doi10.1007/978-3-030-35288-2_31
dc.identifier.cristin1761740
dc.description.localcodeThis article will not be available due to copyright restrictions (c) 2019 by Springeren_US
cristin.unitcode194,63,55,0
cristin.unitnameInstitutt for IKT og realfag
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel