The purpose of this paper is to propose a Web application system for visualizing Twitter users based on temporal changes in the impressions received from the tweets posted…
The purpose of this paper is to propose a Web application system for visualizing Twitter users based on temporal changes in the impressions received from the tweets posted by the users on Twitter.
The system collects a specified user’s tweets posted during a specified period using Twitter API, rates each tweet based on three distinct impressions using an impression mining system, and then generates pie and line charts to visualize results of the previous processing using Google Chart API.
Because there are more news articles featuring somber topics than those featuring cheerful topics, the impression mining system, which uses impression lexicons created from a newspaper database, is considered to be more effective for analyzing negative tweets.
The system uses Twitter API to collect tweets from Twitter. This suggests that the system cannot collect tweets of the users who maintain private timelines. According to our questionnaire, about 30 per cent of Twitter users’ timelines are private. This is one of the limitations to using the system.
The system enables people to grasp the personality of Twitter users by visualizing the impressions received from tweets the users normally post on Twitter. The target impressions are limited to those represented by three bipolar scales of impressions: “Happy/Sad”, “Glad/Angry” and “Peaceful/Strained”. The system also enables people to grasp the context in which keywords are used by visualizing the impressions from tweets in which the keywords were found.
The purpose of this paper is to propose a method of calculating the sentiment value of a tweet based on the emoticon role.
Classification of emoticon roles as four types showing “emphasis”, “assuagement”, “conversion” and “addition”, with roles determined based on the respective relations to sentiment of sentences and emoticons.
Clustering of users of four types based on emoticon sentiment.
Formalization, using regression analysis, of the relation of sentiment between sentences and emoticons in all roles.