Identification of relevant features influencing movie reviews using sentiment analysis

Sentiment analysis is a systematic text mining research that examines individuals' behaviour, approach, and viewpoint. This paper analyses viewers' sentiments towards the movies released during the pandemic. This study employs the sentiment analysis techniques on movie reviews' accessed in real-time from internet movie database (IMDb). The paper's main objective is to identify the potential words that contribute to the biases of the reviews and influence overall viewers. The proposed methodology has employed valence aware dictionary for sentiment reasoning based on sentiment analysis of overall reviews, followed by application to various movie genres. Finally, we have applied Pearson's correlation analysis to find the association between the words among the genres. The paper also calculates the sentiment scores of reviews using different sentiment analysis models. Our results showed a minimum of 17% features common genre-wise. It reveals sets of most distinct influential words, which may be vital for understanding the nature of the language used for a particular kind of movie.