Abstract:
Sentiment Analysis is a rapidly growing field of research due to the explosive growth in digital
information, there is a need to filter out unnecessary information and get meaningful results
out of this huge information. Sentiment Analysis focuses on finding polarity of the expressed
sentiment. The main objective of this paper is to find the impact of age and gender of the user on
the subjectivity of the expressed opinion by examining the differences in the way of expression
taking in consideration user’s age and gender separately.
Psychologically it is always said that different gender and age groups have different ways of
expressing their opinion. Multiple studies have been done to support these claims and in most of
the studies, these differences have been highlighted. Based on these psychological differences,
we create a dataset by collecting reviews on books from facebook users along with their age and
gender information. Different data sets on the basis of age groups (Below 20, 21 - 34, 35 - 50
and Above 50) and gender (male, female) are extracted from this dataset and sentiment analysis
is done using different machine learning approaches along with a dictionary based approach,
Vader. The results are in align with the previous studies on the psychological differences in
different gender and age groups.
