dc.contributor.authorChong, Kah Weng
dc.date.accessioned2017-12-21T01:41:22Z
dc.date.available2017-12-21T01:41:22Z
dc.date.issued2017
dc.identifier.urihttp://hdl.handle.net/10356/73008
dc.description.abstractSentiment analysis often bring information and prediction about opinions. For a large corpus of opinions data on Twitter, it is always not simple to analyze due to different personal expression and the grammar level they use. Moreover, Emoji and slangs, abbreviation bring tougher challenge. Today, having a sentiment analysis tools for Twitter data mining is usefulness in terms of business survey, detection of terrorist mind sets, and for better understanding of particular user. Although the analytic result might not be 100% true and accurate, it create a compare platform that consumer can choose between different brands when comes to choice. On the other hand, detection of terrorist mind sets is always a play-safe strategy especially in current world which more and more terrorist attacked was launched unexpectedly. Lastly, to study a person behavior and properties, sentiment analysis bring great achievement. This program use hybrid approach to cover the brevity, lack of context, same word used to express different sentiments by different users.en_US
dc.format.extent68 p.en_US
dc.language.isoenen_US
dc.rightsNanyang Technological University
dc.subjectDRNTU::Engineering::Electrical and electronic engineeringen_US
dc.titleUser-level twitter polarity classification using a hybrid approachen_US
dc.typeFinal Year Project (FYP)en_US
dc.contributor.supervisorEr Meng Jooen_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.description.degreeBachelor of Engineeringen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record