Detecting Chronic Critics Based on Sentiment Polarity and User’s Behavior in Social Media
Article Structure
Abstract
There are some chronic critics who always complain about the entity in social media.
Introduction
On a social media website, there may be millions of users and large numbers of comments.
Topics
social media
Appears in 16 sentences as: social media (16)
In Detecting Chronic Critics Based on Sentiment Polarity and User’s Behavior in Social Media
- There are some chronic critics who always complain about the entity in social media .Page 1, “Abstract”
- In social media , most comments are informal, and, there are sarcastic and incomplete contexts.Page 1, “Abstract”
- As an alternative approach for social media , we can assume that users who share the same opinions will link to each other.Page 1, “Abstract”
- On a social media website, there may be millions of users and large numbers of comments.Page 1, “Introduction”
- The comments in social media are related to the real world in such fields as marketing and politics.Page 1, “Introduction”
- Analyzing comments in social media has been shown to be effective in predicting the behaviors of stock markets and of voters in elections (Bollen et al., 2011; Tumasjan et al., 2010; O’Connor et al., 2010).Page 1, “Introduction”
- However, it is generally quite difficult for a computer to detect a chronic critic’s comments, since especially the comments in social media are often quite informal.Page 1, “Introduction”
- In contrast, most of the previous work on sentiment analysis in social media does not consider these kinds of problems (Barbosa and Feng, 2010; Davidov et al., 2010; Speriosu et al., 2011).Page 2, “Introduction”
- Switching to the behavior of each user, in social media we often see that users who have similar ideas will tend to cooperate with each other.Page 2, “Introduction”
- For our experiments, we used Twitter, a popular social media service.Page 2, “Introduction”
- (2011) proposed methods to predict a sentiment polarity (i.e., positive or negative) of a comment in social media .Page 2, “Introduction”
See all papers in Proc. ACL 2013 that mention social media.
See all papers in Proc. ACL that mention social media.
Back to top.
sentiment analyzer
Appears in 5 sentences as: sentiment analysis (1) sentiment analyzer (4)
In Detecting Chronic Critics Based on Sentiment Polarity and User’s Behavior in Social Media
- In contrast, most of the previous work on sentiment analysis in social media does not consider these kinds of problems (Barbosa and Feng, 2010; Davidov et al., 2010; Speriosu et al., 2011).Page 2, “Introduction”
- We used the sentiment analyzer created by Kanayama and Na-sukawa (2012) to detect a phrase representing neg-Page 3, “Introduction”
- The sentiment analyzer can find not only sentiment phrases but the targets of the phrases based on syntactic parsing and the case framesl.Page 3, “Introduction”
- However, because there are many informal tweets and because most users omit the grammatical case in tweets, the sentiment analyzer often fails to capture any target.Page 3, “Introduction”
- To address this problem, in addition to a target extracted by the sentiment analyzer , we obtain a target based on the dependency tree.Page 3, “Introduction”
See all papers in Proc. ACL 2013 that mention sentiment analyzer.
See all papers in Proc. ACL that mention sentiment analyzer.
Back to top.
confidence score
Appears in 4 sentences as: confidence score (3) confidence scores (1)
In Detecting Chronic Critics Based on Sentiment Polarity and User’s Behavior in Social Media
- The label propagation assigns a confidence score 0 = (01,...,cm) to each node U 2 ul, ..., um, where the score is a real number between —1 and l. A score close to 1 indicates that we are very confident that the node (user) is a chronic critic.Page 4, “Introduction”
- Thus, by minimizing E(c), we assign the confidence scores considering the results of the opinion mining and agreement relationships among the users.Page 4, “Introduction”
- To avoid this problem, Yin and Tan (2011) introduced a neutral fact, which decreases each confidence score by considering the distance from the seeds.Page 5, “Introduction”
- The neutral fact has a fixed confidence score 0 and connects with all of the nodes except the seeds.Page 5, “Introduction”
See all papers in Proc. ACL 2013 that mention confidence score.
See all papers in Proc. ACL that mention confidence score.
Back to top.
