Description
Movie Review Analysis and Classification using AI
Abstract: Movie Review Analysis and Classification using AI – In this paper, we have evaluated the performance of six machine learning algorithms in terms of sentiment analysis in the IMDB review dataset. Among these algorithms, one is neural network-based, and the other are non-neural network-based. We used binary classification for sentiment analysis in IMDB reviews and examined all the six algorithms to detect whether the sentiment of the text is positive or negative. Among the neural network-based approaches, we applied LSTM. We found that LSTM performed better than ML algorithms. Among the non-neural network-based algorithms, we applied Multinomial Naïve Bayes and Support Vector Machine and random forests and decision tree and logistic regression algorithms. We found that SVM outperformed Multinomial Naïve Bayes. Among these six algorithms, the maximum accuracy level is gained by neural networks is nearly 98%.
Introduction:
As the technology is raising, users can directly give reviews about products, brands, etc. These reviews play a vital role in online shopping as well as help people to determine whether a product is good or not. These reviews or opinions play a significant impact on the success of a business. It helps companies to improve their products based on analyzing user feedback.
The existing model of the system:
- Title: VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text
- Author: Hutto, C., & Gilbert, E.
- Abstract:- Earlier, various rule-based approaches have been used for sentiment analysis. For example, Hutto and Gilbert presented a simple rule-based model for general sentiment analysis and found better performance than the benchmarks used in their study. But the performance of their proposed model was not compared with neural network-based approaches. Popular Social Media website like Twitter has also been used for sentiment analysis.
Design Methodology:
A supervised machine learning model is trained by using three types of historic data: “positive” and “negative” sentiments; The model is trained to predict the probability that a new review should be reported, using information such as previous review sentiments, their earlier behaviors, and their transaction history.
Proposed Work:
We split the data into sequential train and test datasets for all experiments. The train set includes all labeled samples around 80% and the test set includes all labeled samples around 20%. We train each supervised model on the train set using all features and then evaluate them on the entire test set. To measure performance over time. We use the scikit-learn implementation of logistic regression (LR) and random forest (RF), multinomial naive Bayes, decision tree, Support Vector Machine (SVM) and LSTM
MODULES:
- DATA COLLECTION
- DATA PRE-PROCESSING
- FEATURE EXTRACTION
- EVALUATION MODEL
DATA COLLECTION:
Data used in this paper is a set of movie reviews collected of movies. This step is concerned with selecting the subset of all available data that you will be working with. ML problems start with data preferably, lots of data (examples or observations) for which you already know the target answer. Data for which you already know the target answer is called labeled data.
DATA PRE-PROCESSING:
Organize your selected data by formatting, cleaning, and sampling from it.
SYSTEM ARCHITECTURE: Movie Review Analysis and Classification using AI
HARDWARE AND SOFTWARE SPECIFICATION
Movie Review Analysis and Classification using AI
Hardware:
1 GB RAM
80 GB Hard Disk
Intel Processor
LAN
Software :
Windows OS
Python GUI or Anaconda Navigator
System Requirement:
Operating System: Windows 7 Ultimate 32 bit / Windows XP
Customer Reviews
There are no reviews yet.