Whether intentionally or not, many individuals in society express some form of prejudice or bias in their thinking and communications. Prejudice can be expressed in a multitude of ways and may be directed towards anything in which people can have an opinion. What makes prejudiced/biased thinking different and potentially more dangerous than having an opinion is that they are not always based on one's personal experiences and therefore may be misinformed. With the rise of social media platforms in the last 20 years or so, people have more ways than ever to express their opinions and share their voices. This paper defines an approach to using Twitter, one of the most popular modern-day social media platforms, to analyze an individual's tweets for the purposes of identifying potential biases. Using sentiment analysis along with other natural language processing tools, a score of potential bias of an individual user is calculated. This score can provide insight to the degree and/or frequency at which a person can be expected to exhibit biased behavior or make biased statements and is only meant to serve as a reference.
[1]
Chien-Chung Chan,et al.
Text Mining for Sentiment Analysis of Twitter Data
,
2012
.
[2]
C. Arnsperger,et al.
More than Modus Vivendi, less than Overlapping Consensus: towards a Political Theory of Social Compromise
,
2004
.
[3]
Haliyana Khalid,et al.
Sentiment Analysis in Social Media and Its Application: Systematic Literature Review
,
2019,
Procedia Computer Science.
[4]
Ghaida S. Alorini,et al.
Machine Learning Enabled Sentiment Index Estimation Using Social Media Big Data
,
2020,
2020 SoutheastCon.
[5]
Vishal. A. Kharde,et al.
Sentiment Analysis of Twitter Data : A Survey of Techniques
,
2016,
ArXiv.