JUMRv1: A Sentiment Analysis Dataset for Movie Recommendation

Abstract

Nowadays, we can observe the applications of machine learning in every field, ranging from the quality testing of materials to the building of powerful computer vision tools. One such recent application is the recommendation system, which is a method that suggests products to users based on their preferences. In this paper, our focus is on a specific recommendation system called movie recommendation. Here, we make use of user reviews of movies in order to establish a general outlook about the movie and then use that outlook to recommend that movie to other users. However, a huge number of available reviews has baffled sophisticated review systems. Consequently, there is a need to find a method of extracting meaningful information from the available reviews and use that in classifying a movie review and predicting the sentiment in each one. In a typical scenario, a review can either be positive, negative, or indifferent about a movie. However, the available research articles in the field mainly consider this as a two-class classification problem—positive and negative. The most popular work in this field was performed on Stanford and Rotten Tomatoes datasets, which are somewhat outdated. Our work is based on self-scraped reviews from the IMDB website, and we have annotated the reviews into one of the three classes—positive, negative, and neutral. Our dataset is called JUMRv1—Jadavpur University Movie Recommendation dataset version 1. For the evaluation of JUMRv1, we took an exhaustive approach by testing various combinations of word embeddings, feature selection methods, and classifiers. We also analysed the performance trends, if there were any, and attempted to explain them. Our work sets a benchmark for movie recommendation systems that is based on the newly developed dataset using a three-class sentiment classification.

Tweets Emotions Analysis of Community Activities Restriction as COVID-19 Policy in Indonesia Using Support Vector Machine

“…(10) and (11). In addition, the highest Chi-Square value indicates that a feature is very informative or helpful for a classification process [46].…”

A Method of Domain Dictionary Construction for Electric Vehicles Disassembly

“…There are many algorithms for generating domain-specific dictionaries and many scholars who have conducted research on them. In terms of a sentiment dictionary, the POS (part-of-speech) tag is utilized to generate the sentiment dictionary in the field of shopping reviews; the authors in [5] apply POS, occurrence, and frequency to sentiment analysis of user preferences from social media data as well; feature selection and classification are used for a sentiment analysis dataset to recommend movies to other users in [6]; in [10], researchers presented a sentiment analysis-based decision support system by integrating support vector machines with a whale optimization method for autonomously adjusting hyperparameters and conducting feature weighting; the paper in [11] uses topic models, time series analysis, and sentiment analysis to search for rumors in social media texts; in [12], a sentiment analysis of homestay comments dictionary is based on the sentimental PMI algorithm; in [13], a cosine similarity measurement combining word semantic information about TF-IDF method extracts public sentiment keywords from the public opinion on the network.…”

“…For decades, machine learning systems have been used to text feature extraction based on deep learning, but required careful engineering and significant domain expertise to design a feature extractor that transformed the raw data into feature vector. Deep learning learns millions of parameters, features, and feature representations automatically from large data, instead of adopting hand-crafted features, which rely heavily on designers' past knowledge [5,6]. Recently, rich literature has been produced on machine learning algorithms, and this may be an effective method for text feature extraction.…”