8/19/2023 0 Comments Imdb raw data set![]() ![]() People generally look into blogs, review sites like IMDb to know the movie cast, crew, reviews, and ratings of other people. These reviews play a vital role in the success of movies or sales of the products ( Agarwal & Mittal, 2016). Reviews are short texts that generally express an opinion about movies or products. In the business sector, companies use SA to derive new strategies based on customer feedback and reviews ( Hand & Adams, 2014 Alpaydin, 2020).īesides the social media platforms, several websites serve as a common platform for discussions about social events, sports, and movies, etc., and the Internet Movie Database (IMDb) is one of the websites that offer a common interface to discuss movies and provide reviews. Many large companies like Amazon, Apple, and Google use the reviews of their employees to analyze the response to various services and policies. Thus, SA helps to increase the popularity and followers of political leaders, as well as, other important personalities. can be used to analyze the perception of people about a personality, service, or product, as well as, used to predict the outcome of various social and political campaigns. Sentiments given on social media platforms like Twitter, Facebook, etc. ![]() The process of mining the sentiment from the texts is called sentiment analysis (SA) and has been regarded as a significant research area during the last few years ( Hearst, 2003). Apart from being inspiring, the ST contains users’ sentiments about a specific personality, topic, or movie and can be leveraged to identify the popularity of the discussed item. These ST take the form of jargon and are even used by search engines as queries. ST has gained significant importance over traditional blogging because of its simplicity and effectiveness to influence the crowd. Shared opinions on social networking sites are generally known as short texts (ST) concerning the length of the posted text ( Sahu & Ahuja, 2016). The rise and wide usage of social media platforms and microblogging websites provide the opportunity to share as you like where people share their opinions on trending topics, politics, movie reviews, etc. In modern times, social media is used for showcasing one’s esteem and prestige by posting photos, text, video clips, etc. People want to share their opinions, ideas, comments, and daily life events on social media. Social media has become an integral part of human lives in recent times. Experimental results on TextBlob assigned sentiments indicate that an accuracy of 92% can be obtained using the proposed model. For tackling this issue, TextBlob is used to assign a sentiment to the dataset containing reviews before it can be used for training. The sentiment classification accuracy of the models is affected due to the contradictions in the user sentiments in the reviews and assigned labels. Experimental results indicate that the SVM obtains the highest accuracy when used with TF-IDF features and achieves an accuracy of 89.55%. Various feature engineering approaches such as term frequency-inverse document frequency (TF-IDF), bag of words, global vectors for word representations, and Word2Vec are applied along with the hyperparameter tuning of the classification models to enhance the classification accuracy. The objective is to find the optimal process and approach to attain the highest accuracy with the best generalization. For this purpose, the reviews are first preprocessed to remove redundant information and noise, and then various classification models like support vector machines (SVM), Naïve Bayes classifier, random forest, and gradient boosting classifiers are used to predict the sentiment of these reviews. ![]() This study provides the implementation of various machine learning models to measure the polarity of the sentiments presented in user reviews on the IMDb website. Despite being helpful to provide the critique of movies, the reviews on IMDb cannot be read as a whole and requires automated tools to provide insights on the sentiments in such reviews. This provides a diverse and large dataset to analyze users’ sentiments about various personalities and movies. The Internet Movie Database (IMDb), being one of the popular online databases for movies and personalities, provides a wide range of movie reviews from millions of users. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |