2014年10月3日 星期五

Emoticons in social media

People increasingly depend on social media to communicate and share information with others nowadays. Besides text, they frequently use emoticons to express their feeling and emotion, such as ^_^.

The rapid growth of social data from such online social networks as Twitter and sina weibo has aroused enormous interest in the mining and discovery of customer insights. But are the emoticons kinds of true reflection of people’s real emotion?

We have to review the concept of sentiment classification which has been mentioned by Rosanna in last week. A document or sentence can be classified by using dictionary-based method. Each word is given a score, along with three different dimensions: positive, negative and objective. By using the same method, we can classify any specific emoticon.

According to the investigation, the top 10 most frequently used emoticons in the corpus are listed in Table 1[1]. It demonstrates that although the number of emoticons is big, only a handful of emoticons are used far more frequently than all others.

                                                     TABLE 1. TOP 10 EMOTICONS


After knowing the sentiment of a specific emoticon, we can analyzing and classify the text content generated by user in sentence level by using dictionary-based method. And we can compare the two scores of emoticon and text sentence to see whether the emoticon reflects the emotion of user correctly.


Reference:

[1] Martin Min, Tanya Lee, Margaret Zhang, Lei Li
Netbase Solutions, Inc. Mountain View, USA 

10 則留言:

  1. I think the sentiment classification is a effective way to predict the result of the competitions which enable the masses to decide the champion, such as the Voice of China.

    回覆刪除
  2. Hi,Guanze,what you mentioned in your blog is really useful.And what to know something about the algorithm to do sentiment classification?Can you give me some opinions?Thanks!

    回覆刪除
  3. Emoticons....wow...it's interesting! like this ^.^, ^.<....I like this topic! I also learned that different country have different habits. For example, the USA people like drawing emoticons like :) :(,but Chinese people mostly like to arrange it as ^_^, just as what I have done in the beginning. It's a interesting phenomenon,right?

    回覆刪除
  4. Hi, Guanze. Frankly speaking, I always prefer using some emoticons in my article such as ^_^ or ^.^. But sometimes I also noticed that emoticons can not be fully representative of a person's mood. So your blog is really useful for me. Thank you.

    回覆刪除
  5. Emoticons are very useful to do sentiment analysis. People often use emoticons to express their emotion. If we take emoticons factor into consideration when doing sentiment analysis, the accuracy will be better. Thank you for your article.

    回覆刪除
  6. Using scores of the text contents to analyze the emoticon, brilliant. The meaning of the emoticon sometimes could be unclear, but the text content always have a clear purpose. So we can use the text to find out the user's emotion behind the emoticon. Thanks for sharing.

    回覆刪除
  7. Your strategy dealing with Emoticons is a bit same with my thought in final presentation but I focus on the words. Build up library for positive words and negative words respectively, when any sentence comes, it will get a score from both two libraries. The final score wil be the answer of these two scores subtracting one from the other.

    回覆刪除
  8. In our assignment one and assignment two, we wiped off the punctuation of the text. I thought when we analyzed natural language in computer, we should do the same things to all the text. But now I find that we would wipe off emoticons of text also! Thank you for your blog, it makes me think a lot.

    回覆刪除
  9. How attractive your blog is. Actually, now emotion word appears usual in social media. However , not every emotion work express user's true mood. And it is worth to be analyze. this blog is very useful

    回覆刪除
  10. Nice sharing. Symbol expressions as emotions are really getting more and more popular nowadays. The study and database building on them is necessary to improve the quality of sentiment analysis. The research methods and material should follow the community creation paces.

    回覆刪除