Research Article
Analysis and Visualization of University Twitter Feeds Sentiment
@INPROCEEDINGS{10.1007/978-3-319-98752-1_15, author={Arlene Caballero and Jasmin Niguidula and Jonathan Caballero}, title={Analysis and Visualization of University Twitter Feeds Sentiment}, proceedings={Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23--24, 2017, Proceedings}, proceedings_a={BDTA}, year={2018}, month={11}, keywords={Social networking Opinion mining Twitter profile Information theory Term frequency-inverse document frequency}, doi={10.1007/978-3-319-98752-1_15} }- Arlene Caballero
Jasmin Niguidula
Jonathan Caballero
Year: 2018
Analysis and Visualization of University Twitter Feeds Sentiment
BDTA
Springer
DOI: 10.1007/978-3-319-98752-1_15
Abstract
The exponential growth of online social network as communication channel brought revolutionary changes in our daily lives. For the organizations, Twitter can be used for many reasons. It can be used as a channel of communication for expressing thoughts, emotions, experiences, perspectives, and opinions in a variety of topics and social interest. This study focused on the information theoretic review of sentiment analysis and visualization in Twitter. This paper examined the tweeter feeds from a select institution using a web-based sentiment analysis tool for analyzing tweeter sentiment and tweet visualization. This further investigates the clustering techniques and information theory applied to visualize and analyze the sentiments in the tweeter feeds using a query as the target of sentiments performed on over 1,500 tweeter feeds from a select institution users. In this study, the individual tweets from the users were converted into images and presented in forms of charts, graphs and diagrams to discover the nature of activity of the users. In view of this, an approach to data mining technique – Shannon information theory has been examined to analyze and review how the estimated sentiment in the corpus of data extracted from the tweeter feeds were processed and calculated. The tf-idf calculated for each query term in tweeter feeds were converted into images using information theoretic approach. With this, the nature of activity and opinions of the users in a select institution were discovered. This study also described the tweeter sentiments in an emotional scatter diagram mapped with pleasure and stimulation using the Russel Model of Affect.