Precision Impact of Emoticons for Social Media Sentiment Analysis

Traditionally, businesses spend tons of money performing customer surveys on brands. In the big data age, such insights including both consumer compliments and complaints can be automatically collected from social media such as twitter. The enabling technology is sentiment analysis. It is observed that social media often uses emoticons such as :) and :( mixed with text to express sentiment. This research presents a novel study of how emoticons can help sentiment analysis precision. Data analysis shows that emoticons alone cannot determine sentiments towards a brand and they can only be used together with other evidence. Further study has discovered a use of emoticons as counter evidence to block glaring errors in sentiment analysis.