Investigation of the Feature Selection Problem for Sentiment Analysis in Arabic Language

Nasser, Ahmed R.; Dincer, Kivanc; Sever, Hayri

doi:10.13053/rcs-110-1-4

Cited by 6 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unigram represented each word as a feature. Several studies have shown that the use of unigrams was better than other 𝑛 − 𝑔𝑟𝑎𝑚 models [17], [18] in supporting classifier performance.…”

Section: Feature Modelmentioning

confidence: 99%

Feature Space Augmentation for Negation Handling on Sentiment Analysis

Ilmawan,

Muladi,

Prasetya

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

One crucial issue affecting the performance of sentiment analysis tasks is negation. Handling negation involves determining the negation scope and negation cue. Feature space augmentation is one approach used to address negation. Feature space augmentation has been carried out by some previous researchers using a negation flag with the rule that the negation scope includes all words from the explicit negation cue to the punctuation mark. This study aimed to analyze the classifier's performance when negation handling was applied by adding a new rule for the negation scope. The new rule for determining the negation scope no longer took all words from the negation cue to the punctuation mark, but only considered or ignored words with certain POS tags. The results of this study showed that using the new rule for negation scope contributed to improving the performance of the classifier in sentiment analysis tasks. The proposed approach for negation handling was better than the previous approach in terms of accuracy, precision, recall, and f1-score.

show abstract

Section: Feature Modelmentioning

confidence: 99%

Feature Space Augmentation for Negation Handling on Sentiment Analysis

Ilmawan,

Muladi,

Prasetya

2023

Ilk. J. Ilm.

View full text Add to dashboard Cite

show abstract

“…A. Nasser et al [16] execute a document level oversaw evaluation examination system for the Arabic setting. They use three assorted part extraction methods to make three datasets.…”

Section: Text Analysismentioning

confidence: 99%

Investigating Text Mining Features and Classifiers: An Experimental Analysis

KaurPabla¹

2020

IJATCSE

View full text Add to dashboard Cite

The proposed work presents the detection of hate speech in social media. In this context, the text mining techniques are valuable. This, in turn, requires an accurate classification algorithm as well as text feature selection technique which works well with the sentiment classification. Therefore, a review of existing techniques is performed first. According to literature, amongst the techniques suggested by the researchers, the GI (Gini Index), DF (document frequency), POS (part of speech) tagging, and IG (information gain)are popular and frequently used techniques for sentiment classification. Thus, these techniques are chosen to implement the text feature selection. Further, the SVM (Support Vector Machine) and KNN (k-Nearest Neighbour) algorithms are applied to classify the selected features. The experimental outcomes show that the SVM is accurate and efficient algorithm for classifying measured features. Additionally, it is seen that the combination of SVM with the feature extraction techniques POS and IG is also time efficient. The proposed work may be extended by use of the prevalent algorithms.

show abstract

“…Sentiment Analysis (SA) is a subdiscipline under NLP that is focused on assigning a sentiment score to a piece of text [1][2][3]. There are mainly two approaches in SA [4]: the first is lexicon-based and uses the sentiment scores of words and phrases within the text [5], whereas the second is based on machine learning techniques [6,7].…”

Section: Introductionmentioning

confidence: 99%

Extending a sentiment lexicon with synonym–antonym datasets: SWNetTR++

Sağlam¹,

Genç²,

Sever³

2019

Turk J Elec Eng & Comp Sci

Self Cite

View full text Add to dashboard Cite

In our previous studies on developing a general-purpose Turkish sentiment lexicon, we constructed SWNetTR-PLUS, a sentiment lexicon of 37K words. In this paper, we show how to use Turkish synonym and antonym word pairs to extend SWNetTR-PLUS by almost 33% to obtain SWNetTR++, a Turkish sentiment lexicon of 49K words. The extension was done by transferring the problem into the graph domain, where nodes are words, and edges are synonymantonym relations between words, and propagating the existing tone and polarity scores to the newly added words using an algorithm we have developed. We tested the existing and new lexicons using a manually labeled Turkish news media corpus of 500 news texts. The results show that our method yielded a significantly more accurate lexicon than SWNetTR-PLUS, resulting in an accuracy increase from 72.2% to 80.4%. At this level, we have now maximized the accuracy rates of translation-based sentiment analysis approaches, which first translate a Turkish text to English and then do the analysis using English sentiment lexicons.

show abstract

Investigation of the Feature Selection Problem for Sentiment Analysis in Arabic Language

Cited by 6 publications

References 22 publications

Feature Space Augmentation for Negation Handling on Sentiment Analysis

Feature Space Augmentation for Negation Handling on Sentiment Analysis

Investigating Text Mining Features and Classifiers: An Experimental Analysis

Extending a sentiment lexicon with synonym–antonym datasets: SWNetTR++

Contact Info

Product

Resources

About