Show simple item record

AuthorKhan, Habib Ullah
AuthorPeacock, Duncan
Available date2020-08-18T08:34:14Z
Publication Date2019
Publication NameInternational Journal of Work Organisation and Emotion
ResourceScopus
ISSN17408938
URIhttp://dx.doi.org/10.1504/IJWOE.2019.104297
URIhttp://hdl.handle.net/10576/15548
AbstractWork organisations are increasingly interested in using sentiment analysis algorithms to get rapid feedback from microblogging platforms such as Twitter. However, real-life posts can differ from the training data. The subject domain may vary or and emojis and emoticons used to clarify, enhance or even reverse the sentiment of a post. This paper studies the effect of emojis, emoticons and subject on polarity classification using nine tweet-related sentiment analysis web services. A web application was developed to extract from the live Twitter stream, and twelve specific research test sets were created. These were labelled by volunteers, uploaded back into the application and then compared against nine different sentiment analysis web services using two- and three-class accuracy measures. Distinct differences were found in the performance of the sentiment analysis web services of organisations. Sentiment analysis web services can vary significantly in classification performance depending and the effect of emoticons and emojis. Copyright - 2019 Inderscience Enterprises Ltd.
Languageen
PublisherInderscience Enterprises Ltd.
SubjectBenchmark
Comparison
Emojis
Emoticons
Polarity classification
Sentiment analysis
Twitter
Web services
TitlePossible effects of emoticon and emoji on sentiment analysis web services of work organisations
TypeConference Paper
Pagination130-161
Issue Number2
Volume Number10


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record