Fuzzy Based Sentiment Classification in the Arabic Language

Biltawi, Mariam; Etaiwi, Wael; Tedmori, Sara; Shaout, Adnan

doi:10.1007/978-3-030-01054-6_42

Cited by 8 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although plethora survey studies extensively addressed the SA in the English language [18], [37] ASA survey research is still modest [38]. Some ASA research studies addressed specific issues [39], [40], while others focused only on specific SA techniques [41], [42]. However, these studies provide only slight insights into ASA, as they did not comprehensively address it [43].…”

Section: Customer Satisfaction and Sentiment Analysismentioning

confidence: 99%

“…Regarding the Twitter data set, we fetched 20,000 Arabic tweets based on specific search keys, similar to the ones used in [6]. We used Python to connect with Twitter's search application programming interface (API) [42]. We used Twitter accounts and some hashtags in Arabic and English that mentioned the company, such as #STC and # ‫_السعودية‬ ‫االتصاال‬ ‫ت‬ .…”

Section: Data Collectionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting STC Customers’ Satisfaction Using Twitter

Almuqren

Cristea

2023

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

The telecom field has changed accordingly with the emergence of new technologies. This is the case with the telecom market in Saudi Arabia, which expanded in 2003 by attracting new investors. As a result, the Saudi telecom market became a viable market [1]. The prevalence of mobile voice service among the population in Saudi Arabia for that, this research aims at mining Arabic tweets to measure customer satisfaction toward Telecom company in Saudi Arabia. This research is a use case for the Saudi Telecom Company (STC) in Saudi Arabia. The contribution of this study will be capitalised as recommendations to the company, based on monitoring in real-time their customers' satisfaction on Twitter and from questionnaire analysis. It is the first work to evaluate customers' satisfaction with telecommunications (telecom) company in Saudi Arabia by using both social media mining and a quantitative method. It has been built a corpus of Arabic tweets, using a Python script searching for real-time tweets that mention Telecom company using the hashtags to monitor the latest sentiments of Telecom customers continuously. The subset is 20,000 tweets that are randomly selected from the dataset, for training the machine-classifier. In addition, we have done the experimented using deep learning network. The results show that the satisfaction for each service ranges between 31.50% and 49.25%. One of the proposed recommendations is using 5G to solve the "Internet Speed" problem, which showed the lowest customer satisfaction, with 31.50%. This paper's main contributions are defining the traceable measurable criteria for customer satisfaction with telecom companies in Saudi Arabia and providing telecom companies' recommendations based on monitoring real-time customers' satisfaction through Twitter.

show abstract

Section: Customer Satisfaction and Sentiment Analysismentioning

confidence: 99%

Section: Data Collectionmentioning

confidence: 99%

Predicting STC Customers’ Satisfaction Using Twitter

Almuqren

Cristea

2023

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

show abstract

“…Biltawi et al [3] suggested a lexicon-based method to compute the emotional score of Arabic text employing a fuzzy logic theory. The suggested method be composed of two primary parts.…”

Section: Literature Reviewmentioning

confidence: 99%

“…','Are our customers pleased by using our products/services or require more?'. We employ sentiment mining tools and techniques to find the relevant answers to these questions [3]. Such as NLP methods for data pre-processing like word stemming, word lemmatization, and effect of negation.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Sentence-Level Classification Using Parallel Fuzzy Deep Learning Classifier

et al. 2021

View full text Add to dashboard Cite

At present, with the growing number of Web 2.0 platforms such as Instagram, Facebook, and Twitter, users honestly communicate their opinions and ideas about events, services, and products. Owing to this rise in the number of social platforms and their extensive use by people, enormous amounts of data are produced hourly. However, sentiment analysis or opinion mining is considered as a useful tool that aims to extract the emotion and attitude from the user-posted data on social media platforms by using different computational methods to linguistic terms and various Natural Language Processing (NLP). Therefore, enhancing text sentiment classification accuracy has become feasible, and an interesting research area for many community researchers. In this study, a new Fuzzy Deep Learning Classifier (FDLC) is suggested for improving the performance of data-sentiment classification. Our proposed FDLC integrates Convolutional Neural Network (CNN) to build an effective automatic process for extracting the features from collected unstructured data and Feedforward Neural Network (FFNN) to compute both positive and negative sentimental scores. Then, we used the Mamdani Fuzzy System (MFS) as a fuzzy classifier to classify the outcomes of the two used deep (CNN+FFNN) learning models in three classes, which are: Neutral, Negative, and Positive. Also, to prevent the long execution time taking by our hybrid proposed FDLC, we have implemented our proposal under the Hadoop cluster. An experimental comparative study between our FDLC and some other suggestions from the literature is performed to demonstrate our offered classifier's effectiveness. The empirical result proved that our FDLC performs better than other classifiers in terms of true positive rate, true negative rate, false positive rate, false negative rate, error rate, precision, classification rate, kappa statistic, F1-score and time consumption, complexity, convergence, and stability.

show abstract

Sentiment analysis using fuzzy logic: A comprehensive literature review

Vashishtha

Gupta

Mittal

2023

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Understanding and comprehending humans' views, beliefs, attitudes, or opinions toward a particular entity is sentiment analysis (SA). Advancements in e‐commerce platforms has led to an abundance of the real‐time and free forms of opinions floating on social media platforms. This real‐world data are imprecise and vague hence fuzzy logic is required to deal with such subjective data. Since opinions can be fuzzy in nature and definitions of opinion words can be elucidated differently; fuzzy logic has witnessed itself as an effective method to capture the expression of opinions. The study presents an elaborate review of the around 170 published research works for SA using fuzzy logic. The primary emphasis is focused on text‐based SA, audio‐based SA, and fusion of text‐audio features‐based SA. This article discusses the various novel ways of classifying fuzzy logic‐based SA research articles, which have not been accomplished by any other review article till date. The article puts forward the importance of SA tasks and identifies how fuzzy logic adds to this importance. Finally, the article outlines a taxonomy for sentiment classification based on the technique‐supervised and unsupervised in the SA models and comprehensively reviews the SA approaches specific to their task. Prominently, this study highlights the suitability of fuzzy‐based SA approaches into five different classes vis‐a‐vis (a) Sentiment Cognition from Words using fuzzy logic, (b) Sentiment Cognition from Phrases using fuzzy logic, (c) Fuzzy‐rule based SA, (d) Neuro‐fuzzy network‐based SA, and (e) Fuzzy Emotion Recognition.This article is categorized under: Algorithmic Development > Text Mining Fundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining

show abstract

Fuzzy Based Sentiment Classification in the Arabic Language

Cited by 8 publications

References 14 publications

Predicting STC Customers’ Satisfaction Using Twitter

Predicting STC Customers’ Satisfaction Using Twitter

Sentence-Level Classification Using Parallel Fuzzy Deep Learning Classifier

Sentiment analysis using fuzzy logic: A comprehensive literature review

Contact Info

Product

Resources

About