Sentiment analysis of big data with intensity analysis by rule engine, 2015
Dsouza, Sherin Ramya
2010-2019
The use of social media is an emerging way for the public to express their views on companies and other organizations. The success of these entities can depend on a positive presence on social media, leading to an increasing interest in understanding public opinion expressed there. This thesis presents a method for gathering and storing a large number of social media posts, analyzing the sentiments expressed, and further classifying the specific emotions conveyed. The social media platform Twitter was used as a source of millions of publicly viewable posts. The big data software tools Twitter4j, Apache Hadoop, and Apache Hive were used to gather and store these posts. These were then classified as communicating a positive, negative, or neutral sentiment through the technique of sentiment analysis, performed using the tool Lingpipe. To further identify the particular emotions expressed in the Tweet, a rule engine, specifically the DROOLS software, was used.
text
application/pdf
2015-12-01
thesis
Master of Science (MS)
Clark Atlanta University
Computer and Information Sciences
Georgia--Atlanta
http://hdl.handle.net/20.500.12322/cau.td:2015_dsouza_sherin_r