Discriminative Feature Spamming Technique for Roman Urdu Sentiment Analysis

Mehmood, Khawar; Essam, Daryl; Shafi, Kamran; Malik, Misbah

doi:10.1109/access.2019.2908420

Cited by 34 publications

(18 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section of the study outlines the studies that discuss the different shortcomings and opportunities for the area of Urdu-based SA. The existing literature regarding Urdu-based sentiment analysis, when summarized, reflects the various challenges such as non-availability of open access Urdu corpora ( Raza et al, 2019 ), limitation of existing language constructs for the Urdu language like (slangs and emotions-based sentences) ( Marrese-Taylor, Velásquez & Bravo-Marquez, 2014 ), a limited collection of negation and revised modifiers ( Mehmood et al, 2019a ). The need for more domain-centric words for Urdu language ( Khattak et al, 2021 ; Hasan et al, 2018 ).…”

Section: Assessment and Discussion Of Research Questionsmentioning

confidence: 99%

Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study

Liaqat

Hassan

Shoaib

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

Sentiment analysis in research involves the processing and analysis of sentiments from textual data. The sentiment analysis for high resource languages such as English and French has been carried out effectively in the past. However, its applications are comparatively few for resource-poor languages due to a lack of textual resources. This systematic literature explores different aspects of Urdu-based sentiment analysis, a classic case of poor resource language. While Urdu is a South Asian language understood by one hundred and sixty-nine million people across the planet. There are various shortcomings in the literature, including limitation of large corpora, language parsers, and lack of pre-trained machine learning models that result in poor performance. This article has analyzed and evaluated studies addressing machine learning-based Urdu sentiment analysis. After searching and filtering, forty articles have been inspected. Research objectives have been proposed that lead to research questions. Our searches were organized in digital repositories after selecting and screening relevant studies. Data was extracted from these studies. Our work on the existing literature reflects that sentiment classification performance can be improved by overcoming the challenges such as word sense disambiguation and massive datasets. Furthermore, Urdu-based language constructs, including language parsers and emoticons, context-level sentiment analysis techniques, pre-processing methods, and lexical resources, can also be improved.

show abstract

Section: Assessment and Discussion Of Research Questionsmentioning

confidence: 99%

Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study

Liaqat

Hassan

Shoaib

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Manual Annotation, Auto-annotation and Semi Auto-annotation. In this study, manual annotation was performed to label the reviews into their targeted class according to the guidelines presented in [44] and [45]. Each review was labelled with one of the two classes-Positive or negative.…”

Section: Corpus Generationmentioning

confidence: 99%

Sentiment Analysis of Reviews in Natural Language: Roman Urdu as a Case Study

Qureshi

Asif

Hassan³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Opinion Mining from user reviews is an emerging field. Sentiment Analysis of Natural Language text helps us in finding the opinion of the customers. These reviews can be in any language e.g. English, Chinese, Arabic, Japanese, Urdu, and Hindi. This research presents a model to classify the polarity of the review(s) in Roman Urdu text (reviews). For the purpose, raw data was scraped from the reviews of 20 songs from Indo-Pak Music Industry. In this research a new dataset of 24000 reviews of Roman Urdu text is created. Nine Machine Learning algorithms-Naïve Bayes, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, Artificial Neural Networks, Convolutional Neural Network, Recurrent Neural Networks, ID3 and Gradient Boost Tree, are attempted. Logistic Regression outperformed the rest, based on testing and cross validation accuracies that are 92.25% and 91.47% respectively.

show abstract

“…While bag-of-words based feature representation approaches face the problem of data sparsity, randomly initialized word embeddings do not capture the semantics of text and fail to overshadow the performance of pre-trained neural word embeddings. Moreover, most of the existing work [19], [54], [20], [61], [55], [59], [56], [57] employs machine learning based methodologies, only Ghulam et al [62] have utilized a deep learning based approach for the task of Roman Urdu sentiment analysis. Also, no public benchmark dataset is available for Roman Urdu sentiment analysis…”

Section: Contributions: a Review Of Novel Work With Anticipated Imentioning

confidence: 99%

“…They reported that WordNet and TextBlob were highly accurate in word sense disambiguation and largely assisted the classifier to detect polarity in political reviews. Mehmood et al [51] presented a novel feature representation approach namely "Discriminative Feature Spamming" for Roman Urdu sentiment analysis. They compared the performance of the presented approach with TF, Binary Weighting, TF-IDF with word and character level features using Naive Bayes, Logistic Regression, majority voting, weighted voting, and multi-layer perceptron.…”

Section: Roman Urdu Sentiment Analysismentioning

confidence: 99%

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

Discriminative Feature Spamming Technique for Roman Urdu Sentiment Analysis

Cited by 34 publications

References 43 publications

Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study

Sentiment analysis techniques, challenges, and opportunities: Urdu language-based analytical study

Sentiment Analysis of Reviews in Natural Language: Roman Urdu as a Case Study

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

Contact Info

Product

Resources

About