An Efficient Way of Finding Polarity of Roman Urdu Reviews by using Boolean Rules

Sadia, Halima; Ullah, Mohib; Hussain, Takasar; Gul, Nida; Hussain, Muhammad Farooq; Haq, Nazrul; Bakar, Abu

doi:10.12694/scpe.v21i2.1638

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Roman Urdu sentiments for both annotated and nonannotated experimental datasets are crawled and parsed using BeautifulSoup 18 . Neural word embeddings are learned from an enormous non-annotated corpus using Gensim 19 .…”

Section: Experimental Setup and Resultsmentioning

confidence: 99%

“…A very limited sentiment analysis work exists for Roman Urdu which can be classified into lexicon based [18], machine learning, and deep learning based approaches [19], [20], [21], [22]. Lexicon based approaches have low applicability over unseen data, and machine learning based approaches predominantly use bag-of-words based feature representation approaches which face the problem of data sparsity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Precisely Xtreme-Multi Channel Hybrid Approach for Roman Urdu Sentiment Analysis

et al. 2020

View full text Add to dashboard Cite

In order to accelerate the performance of various Natural Language Processing tasks for Roman Urdu, this paper for the very first time provides 3 neural word embeddings prepared using most widely used approaches namely Word2vec, FastText, and Glove. The integrity of generated neural word embeddings is evaluated using intrinsic and extrinsic evaluation approaches. Considering the lack of publicly available benchmark datasets, it provides a first-ever Roman Urdu public dataset which consists of 3241 sentiments annotated against positive, negative, and neutral classes. To provide benchmark baseline performance over the presented dataset for Roman Urdu sentiment analysis, we adapt diverse machine learning (Support Vector Machine, Logistic Regression, Naive Bayes), deep learning (convolutional neural network, recurrent neural network), and hybrid deep learning approaches. Performance impact of generated neural word embeddings based representation is compared with other most widely used bag of words based feature representation approaches using diverse machine and deep learning classifiers. In order to improve the performance of Roman Urdu sentiment analysis, it proposes a novel precisely extreme multi-channel hybrid methodology which makes use of convolutional and recurrent neural networks along with pre-trained neural word embeddings. The proposed hybrid approach outperforms adapted machine learning approaches by the significant figure of 9% and deep learning approaches by the figure of 4% in terms of F1-score. INDEX TERMS Fast-Text, Glove, Pretrain word embeddings for Roman Urdu, Roman Urdu Sentiment Analysis, Word2Vec,

show abstract

Section: Experimental Setup and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Precisely Xtreme-Multi Channel Hybrid Approach for Roman Urdu Sentiment Analysis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Despite having noise and different syntax, the pair Roman Urdu-Urdu obtained an accuracy of 85%, and the English-Urdu pair achieved 45% accuracy. Sadia et al (2020) presented a Boolean rules-based opinion mining parser to find polarity in the Roman Urdu text. The set of Boolean rules classified a user posted/written review as positive, negative, or neutral.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Sadia et al (2020) presented a Boolean rules-based opinion mining parser to find polarity in the Roman Urdu text. The set of Boolean rules classified a user posted/written review as positive, negative, or neutral.…”

Section: Literature Reviewmentioning

confidence: 99%

Count Me Too: Sentiment Analysis of Roman Sindhi Script

Alvi,

Mahoto,

Reshan

et al. 2023

SAGE Open

View full text Add to dashboard Cite

Social media has given voice to people around the globe. However, all voices are not counted due to the scarcity of lexical computational resources. Such resources could harness the torrent of social media text data. Computational resources for rich languages such as English are available. More are being developed, meanwhile strengthening and enhancing the current ones. However, Roman Sindhi, a resource-poor writing style, is a phonetically rich language lacking computational resources, creating a working space for researchers. This work attempts to develop lexical sentiment resources that will help calculate the public opinion expressed in Roman Sindhi and bring their point of view into the limelight. This work is one of the initial efforts to develop lexical Roman Sindhi sentiment dictionary resources to help detect sentiment orientation in a text. Furthermore, it also developed two interfaces to leverage the lexical resources—a Roman Sindhi to English translator (RoSET) that translates a Roman Sindhi feature into an equivalent English word and a Roman Sindhi rule-based sentiment scorer ( RBRS3) that assigns sentiment score to a Roman Sindhi script features. The results obtained from the developed system accommodated the bilingual dataset (Roman Sindhi + English) more adequately. An increase of 20.8% was recorded for positive sentence detection, and a 16% increase was obtained for negative sentences, whereas neutral sentences were marginalized to a lower number (59.31% decrease). The resultant system makes those public voices expressed in the Roman Sindhi script get counted, which otherwise are in vain.

show abstract

“…Authors Pre-processing Techniques [36] Afraz Z. Syed Normalization, Segmentation [37] Afraz Z. Syed Normalization, Diacritic Omission, Tokenization, Segmentation [38] Zia Ul Rehman Tokenization, Calculate Polarity, Polarity Identification [39] Faiza Hashim POS tagging, Data cleaning [40] Kamran Amjad Tokenization, POS Tagging [41] Muhammad Yaseen Khan Normalization, Tokenization, Stop words removal, Special characters removal [42] Neelam Mukhtar Preprocessing is not performed in this paper [12] Hussain Ghulam Preprocessing is not performed in this paper [13] Neelam Mukhtar Stop words removal [14] Neelam Mukhtar Stop words removal [15] Muhammad Hassan POS Tagging, Stop words removal, Tokenization, [16] Ali Hasan Stop words removal [17] Khairullah Khan Noise removal, Tokenization, POS Tagging, Sentence boundary detection [18] Raheela Bibi Stop words removal, POS Tagging [33] Khawar Mehmood Preprocessing is not performed in this paper [19] Neelam Mukhtar Preprocessing is not performed in this paper [20] Neelam Mukhtar POS Tagging [21] Muhammad Yaseen Khan Data cleaning, Tokenization, POS Tagging [22] Daryl Essam Normalization [23] Faizan ul Mustafa Tokenization, Text cleaning, Stop words removal, Stemming [24] Asad Khattak Preprocessing is not performed in this paper [34] Halima Sadia Remove Noise, Tokenization, Stop words removal [25] Sadaf Rani Stop words removal Previous studies have proposed a broad range of techniques and methods to resolve the USA problem. This figure demonstrates the maximum techniques used in USA [46].…”

Section: Referencementioning

confidence: 99%

Urdu Sentiment Analysis: Future Extraction, Taxonomy, and Challenges

Mashooq,

Riaz,

Farooq

2022

VFAST trans. softw. eng.

View full text Add to dashboard Cite

By the newly gained attention from several research areas for the field of opinion mining, work in Sentiment Analysis (SA) has also been increased. Sentiment analysis is actually a natural language processing (NLP) method which is implemented to decide whether the data is negative, positive or neutral. This analysis can also utilized to provide most appropriate countermeasures for various issues that are connected with particular fields. It is a contextual extraction and arrangement of text which recognizes and pinpoints subjective information regarding source material and helps to understand the social sentiment of people while monitoring online conversations, comments, tweets, or information on blogs, etc. There is wide utilization of Urdu language in offering perspectives that's why the Urdu language also wants opinion mining as well. In this research, a systematic literature review on sentiment analysis of Urdu language has been performed. This SLR is focusing on explicit research questions and afterward contributions are described appropriately. The findings of the review present a taxonomy that is based on the techniques of sentiment classification. Furthermore, in this SLR, we have extracted all the preprocessing techniques that were used in these 24 papers, the most adopted algorithms by the researchers, the most implemented sentiment analysis approach, and the feature extraction techniques are also extricated. Eventually, a thorough survey is given on all these considerations. After a detailed and deep evaluation, we have computed their accuracy results for better understanding of future researchers.

show abstract

An Efficient Way of Finding Polarity of Roman Urdu Reviews by using Boolean Rules

Cited by 4 publications

References 0 publications

A Precisely Xtreme-Multi Channel Hybrid Approach for Roman Urdu Sentiment Analysis

A Precisely Xtreme-Multi Channel Hybrid Approach for Roman Urdu Sentiment Analysis

Count Me Too: Sentiment Analysis of Roman Sindhi Script

Urdu Sentiment Analysis: Future Extraction, Taxonomy, and Challenges

Contact Info

Product

Resources

About