Bilingual sentiment detection - Investigating impact of tweet translation

• Main Authors: Vimala, B., Kaur, W.
• Format: Conference or Workshop Item
• Language: English
• Published: 2016
• Subjects: QA75 Electronic computers. Computer science; T Technology (General)
• Online Access: http://eprints.um.edu.my/15865/1/0001.pdf; http://eprints.um.edu.my/15865/

This paper looks at how translating tweets from Malay to English may impact its sentiment score, and if at all the score can be improved in case a tweet is translated compared to just translating the keywords. Tweets written in Malay were translated using an online dictionary before proceeding for analysis. An online sentiment analysis tool, Twin word was used to perform the sentiment analysis on both translated and untranslated tweets. The results of the analysis showed translating tweets did not create a significant impact on the overall sentiment score; therefore translating the whole length of the tweet would not affect the accuracy score.