Feature-based Sentiment Analysis for Slang Arabic Text

Sentiment analysis is the process of determining the attitude or the emotional state of a text automatically. Many algorithms are proposed for this task including ensemble methods, which have the potential to decrease error rates of the individual base learners considerably. In many machine learning tasks and especially in sentiment analysis, extracting informative features is as important as developing sophisticated classifiers. In this study, a stacked ensemble method is proposed for sentiment analysis, which systematically combines six feature extraction methods and three classifiers. The proposed method obtains cross-validation accuracies of 89.6%, 90.7% and 67.2% on large movie, Turkish movie and SemEval-2017 datasets, respectively, outperforming the other classifiers. The accuracy improvements are shown to be statistically significant at the 99% confidence level by performing a Z-test.

Download Full-text

Application of Sentiment Analysis in Movie reviews

Advances in Business Information Systems and Analytics - Sentiment Analysis and Knowledge Discovery in Contemporary Business ◽

10.4018/978-1-5225-4999-4.ch006 ◽

2019 ◽

pp. 77-90 ◽

Cited By ~ 5

Author(s):

ThippaReddy Gadekallu ◽

Akshat Soni ◽

Deeptanu Sarkar ◽

Lakshmanna Kuruva

Keyword(s):

Sentiment Analysis ◽

Experimental Work ◽

Opinion Mining ◽

Rating Systems ◽

Domain Specific ◽

Analysis Process ◽

The People ◽

Textual Data ◽

Feature Based ◽

The Web

Sentiment analysis is a sub-domain of opinion mining where the analysis is focused on the extraction of emotions and opinions of the people towards a particular topic from a structured, semi-structured, or unstructured textual data. In this chapter, the authors try to focus the task of sentiment analysis on IMDB movie review database. This chapter presents the experimental work on a new kind of domain-specific feature-based heuristic for aspect-level sentiment analysis of movie reviews. The authors have devised an aspect-oriented scheme that analyzes the textual reviews of a movie and assign it a sentiment label on each aspect. Finally, the authors conclude that incorporating syntactical information in the models is vital to the sentiment analysis process. The authors also conclude that the proposed approach to sentiment classification supplements the existing rating movie rating systems used across the web and will serve as base to future researches in this domain.

Download Full-text

Deep Learning for Sentiment Analysis of Arabic Text

Proceedings of the ArabWIC 6th Annual International Conference Research Track on - ArabWIC 2019 ◽

10.1145/3333165.3333185 ◽

2019 ◽

Author(s):

Ayah Soufan

Keyword(s):

Deep Learning ◽

Sentiment Analysis ◽

Arabic Text

Download Full-text

Feature-Based Opinion Mining and Managed Machine Learning with Sentiment Classification Models

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.b4555.129219 ◽

2019 ◽

Vol 9 (2) ◽

pp. 3992-3998

Keyword(s):

Machine Learning ◽

Sentiment Analysis ◽

Language Processing ◽

Opinion Mining ◽

Machine Learning Algorithms ◽

Support Vector ◽

K Nearest Neighbors ◽

Data Intensive ◽

Learning Tasks ◽

Feature Based

Sentiment Analysis is individuals' opinions and feedbacks study towards a substance, which can be items, services, movies, people or events. The opinions are mostly expressed as remarks or reviews. With the social network, gatherings and websites, these reviews rose as a significant factor for the client’s decision to buy anything or not. These days, a vast scalable computing environment provides us with very sophisticated way of carrying out various data-intensive natural language processing (NLP) and machine-learning tasks to examine these reviews. One such example is text classification, a compelling method for predicting the clients' sentiment. In this paper, we attempt to center our work of sentiment analysis on movie review database. We look at the sentiment expression to order the extremity of the movie reviews on a size of 0(highly disliked) to 4(highly preferred) and perform feature extraction and ranking and utilize these features to prepare our multilabel classifier to group the movie review into its right rating. This paper incorporates sentiment analysis utilizing feature-based opinion mining and managed machine learning. The principle center is to decide the extremity of reviews utilizing nouns, verbs, and adjectives as opinion words. In addition, a comparative study on different classification approaches has been performed to determine the most appropriate classifier to suit our concern problem space. In our study, we utilized six distinctive machine learning algorithms – Naïve Bayes, Logistic Regression, SVM (Support Vector Machine), RF (Random Forest) KNN (K nearest neighbors) and SoftMax Regression.

Download Full-text