With the advent of Web 2.0, people became more eager to express and share their opinions on web regarding day-to-day activities and global issues as well. Evolution of social media has also contributed immensely to these activities, thereby providing us a transparent platform to share views across the world. These electronic Word of Mouth (eWOM) statements expressed on the web are much prevalent in business and service industry to enable customer to share his/her point of view. In the last one and half decades, research communities, academia, public and service industries are working rigorously on sentiment analysis, also known as, opinion mining, to extract and analyze public mood and views. In this regard, this paper presents a rigorous survey on sentiment analysis, which portrays views presented by over one hundred articles published in the last decade regarding necessary tasks, approaches, and applications of sentiment analysis. Several sub-tasks need to be performed for sentiment analysis which in turn can be accomplished using various approaches and techniques. This survey covering published literature during 2002-2015, is organized on the basis of sub-tasks to be performed, machine learning and natural language processing techniques used and applications of sentiment analysis. The paper also presents open issues and along with a summary table of a hundred and sixty-one articles.

A survey on opinion mining and sentiment analysis

Sentiment analysis

Deep Learning-based Text Understanding (DLTU) is the backbone technique behind various applications, including question answering, machine translation, and text classification. Despite its tremendous popularity, the security vulnerabilities of DLTU are still largely unknown, which is highly concerning given its increasing use in security-sensitive applications such as sentiment analysis and toxic content detection. In this paper, we show that DLTU is inherently vulnerable to adversarial text attacks, in which maliciously crafted texts trigger target DLTU systems and services to misbehave. Specifically, we present TextBugger, a general attack framework for generating adversarial texts. In contrast to prior works, TextBugger differs in significant ways: (i) effective -- it outperforms state-of-the-art attacks in terms of attack success rate; (ii) evasive -- it preserves the utility of benign text, with 94.9\% of the adversarial text correctly recognized by human readers; and (iii) efficient -- it generates adversarial text with computational complexity sub-linear to the text length. We empirically evaluate TextBugger on a set of real-world DLTU systems and services used for sentiment analysis and toxic content detection, demonstrating its effectiveness, evasiveness, and efficiency. For instance, TextBugger achieves 100\% success rate on the IMDB dataset based on Amazon AWS Comprehend within 4.61 seconds and preserves 97\% semantic similarity. We further discuss possible defense mechanisms to mitigate such attack and the adversary's potential countermeasures, which leads to promising directions for further research.

TextBugger: Generating Adversarial Text Against Real-world Applications

Sentiments or opinions from social media provide the most up-to-date and inclusive information, due to the proliferation of social media and the low barrier for posting the message. Despite the growing importance of sentiment analysis, this area lacks a concise and systematic arrangement of prior efforts. It is essential to: (1) analyze its progress over the years, (2) provide an overview of the main advances achieved so far, and (3) outline remaining limitations. Several essential aspects, therefore, are addressed within the scope of this survey. On the one hand, this paper focuses on presenting typical methods from three different perspectives (task-oriented, granularity-oriented, methodology-oriented) in the area of sentiment analysis. Specifically, a large quantity of techniques and methods are categorized and compared. On the other hand, different types of data and advanced tools for research are introduced, as well as their limitations. On the basis of these materials, the essential prospects lying ahead for sentiment analysis are identified and discussed.

A survey of sentiment analysis in social media

Growth in the area of opinion mining and sentiment analysis has been rapid and aims to explore the opinions or text present on different platforms of social media through machine-learning techniques with sentiment, subjectivity analysis or polarity calculations. Despite the use of various machine-learning techniques and tools for sentiment analysis during elections, there is a dire need for a state-of-the-art approach. To deal with these challenges, the contribution of this paper includes the adoption of a hybrid approach that involves a sentiment analyzer that includes machine learning. Moreover, this paper also provides a comparison of techniques of sentiment analysis in the analysis of political views by applying supervised machine-learning algorithms such as Naive Bayes and support vector machines (SVM).

Machine Learning-Based Sentiment Analysis for Twitter Accounts

Sentiment analysis algorithms and applications: A survey

This paper proposes a methodology for generating a stopword list from online social network (OSN) corpora in Egyptian Dialect (ED). The aim of the paper is to investigate the effect of removing ED stopwords on the Sentiment Analysis (SA) task. The stopwords lists generated before were on Modern Standard Arabic (MSA) which is not the common language used in OSN. We have generated a stopword list of Egyptian dialect to be used with the OSN corpora. We compare the efficiency of text classification when using the generated list along with previously generated lists of MSA and combining the Egyptian dialect list with the MSA list. The text classification was performed using Naive Bayes and Decision Tree classifiers and two feature selection approaches, unigram and bigram. The experiments show that removing ED stopwords give better performance than using lists of MSA stopwords only.

/pdf/egyptian-dialect-stopword-list-generation-from-social-1ormfozug0.pdf

Egyptian Dialect Stopword List Generation from Social Network Data

This paper proposes a framework for preparing and using corpora from online social networks and review sites for sentiment analysis task. The framework consists of three phases. The first phase is the preprocessing and cleaning of data collected, then data annotation. The second phase is applying various text processing techniques including: removing stopwords, replacing the negation words and the following negated words with the antonyms of the negated words, and using selective words of part-of-speech tags (adjectives and verbs) on the prepared corpora. The third phase is text classification using Naive Bayes and Decision Tree classifiers and two feature selection approaches, unigrams and bigrams. The experiments show that the data is extremely unbalanced. The results show that applying text processing techniques improve the classification accuracy of the Naive Bayes classifier and reduce the training time of both classifiers. The results also show that Decision tree classifier is more suitable for imbalance data.

http://ieeexplore.ieee.org/iel7/6994955/7008990/07009006.pdf

A framework of preparing corpora from social network sites for sentiment analysis

This paper proposes a methodology to prepare corpora in Arabic language from online social network (OSN) and review site for Sentiment Analysis (SA) task. The paper also proposes a methodology for generating a stopword list from the prepared corpora. The aim of the paper is to investigate the effect of removing stopwords on the SA task. The problem is that the stopwords lists generated before were on Modern Standard Arabic (MSA) which is not the common language used in OSN. We have generated a stopword list of Egyptian dialect and a corpus-based list to be used with the OSN corpora. We compare the efficiency of text classification when using the generated lists along with previously generated lists of MSA and combining the Egyptian dialect list with the MSA list. The text classification was performed using Naive Bayes and Decision Tree classifiers and two feature selection approaches, unigrams and bigram. The experiments show that the general lists containing the Egyptian dialects words give better performance than using lists of MSA stopwords only.

Corpora Preparation and Stopword List Generation for Arabic data in Social Network

This paper proposes a methodology for generating a stopword list from online social network (OSN) corpora in Egyptian Dialect(ED). The aim of the paper is to investigate the effect of removingED stopwords on the Sentiment Analysis (SA) task. The stopwords lists generated before were on Modern Standard Arabic (MSA) which is not the common language used in OSN. We have generated a stopword list of Egyptian dialect to be used with the OSN corpora. We compare the efficiency of text classification when using the generated list along with previously generated lists of MSA and combining the Egyptian dialect list with the MSA list. The text classification was performed using Na\"ive Bayes and Decision Tree classifiers and two feature selection approaches, unigram and bigram. The experiments show that removing ED stopwords give better performance than using lists of MSA stopwords only.

Hoda Korashy

Papers

Sentiment analysis algorithms and applications: A survey

Egyptian Dialect Stopword List Generation from Social Network Data

A framework of preparing corpora from social network sites for sentiment analysis

Corpora Preparation and Stopword List Generation for Arabic data in Social Network

Egyptian Dialect Stopword List Generation from Social Network Data