A Domain-Independent Classification Model for Sentiment Analysis Using Neural Models

Nour Jnoub,Wolfgang Klas,Fadi Al Machot

doi:10.3390/app10186221

Nour Jnoub, Wolfgang Klas + Show 1 more

Open Access

https://doi.org/10.3390/app10186221

Copy DOI

Abstract

Most people nowadays depend on the Web as a primary source of information. Statistical studies show that young people obtain information mainly from Facebook, Twitter, and other social media platforms. By relying on these data, people may risk drawing the incorrect conclusions when reading the news or planning to buy a product. Therefore, systems that can detect and classify sentiments and assist users in finding the correct information on the Web is highly needed in order to prevent Web surfers from being easily deceived. This paper proposes an intensive study regarding domain-independent classification models for sentiment analysis that should be trained only once. The study consists of two phases: the first phase is based on a deep learning model which is training a neural network model once after extracting robust features and saving the model and its parameters. The second phase is based on applying the trained model on a totally new dataset, aiming at correctly classifying reviews as positive or negative. The proposed model is trained on the IMDb dataset and then tested on three different datasets: IMDb dataset, Movie Reviews dataset, and our own dataset collected from Amazon reviews that rate users’ opinions regarding Apple products. The work shows high performance using different evaluation metrics compared to the stat-of-the-art results.

Highlights

Sentiment analysis is the task of recognizing positive and negative opinions of users regarding different purposes, e.g., users’ opinions about movies, products, music albums, and many other fields
The study consists of two phases: the first phase is based on a deep learning model which is training a neural network model once after extracting robust features and saving the model and its parameters
In order to gain sufficient information and prove the applicability of our approach, the following libraries have been used: NLTK library for natural language processing, Keras (Deep learning) and scikit-learn, which is mainly used for testing the performance of the other classifiers

Summary

Introduction

Sentiment analysis is the task of recognizing positive and negative opinions of users regarding different purposes, e.g., users’ opinions about movies, products, music albums, and many other fields. There are different types of sentiment analysis, the most popular types are classified and described in the following: Grained Sentiment Analysis: The results in this type are more than binary classification results where two labels (positive, negative) are presented. It is achieved in fine-grained granularity varying from strong negative, weakly negative, neutral, weakly positive to strong positive based on the determined polarity, mainly used when the polarity precision is highly important and binary results like negative or positive could not be useful and may provide incorrect classifications [2]. Sophisticated machine learning algorithms [3] are used to detect emotions for different goals

Results

Discussion

Conclusion