Urdu Sentiment Analysis With Deep Learning Methods

Abstract

Although over 169 million people in the world are familiar with the Urdu language and a large quantity of Urdu data is being generated on different social websites daily, very few research studies and efforts have been completed to build language resources for the Urdu language and examine user sentiments. This study is focused on Urdu sentiment analysis of user reviews. After collecting Urdu user reviews about different genres from different websites, Urdu user reviews were annotated by three human experts. The primary objective of this study is twofold: (1) develop a benchmark dataset for resource-deprived Urdu language for sentiment analysis and (2) evaluate various machine learning and deep learning sentiment analysis models. Six machine learning and two deep learning classifiers, random forest (RF), naïve Bayes, support vector machine (SVM), AdaBoost, multilayer perceptron (MLP), logistic regression, LSTM, and CNN1D, are implemented. The results of all machine learning models are compared on the basis of different N-gram feature models. We implement all the above mentioned machine learning classifiers with unigram, bigram, trigram, uni-bigram, and uni-trigram features and deep learning models with the FastText word embedding model. Finally, the results of all classifiers are analyzed. The logistic regression model outperforms all other models in terms of accuracy of 0.8194, precision of 0.7995, recall of 0.8426, and an F1 measure of 0.8205 with the uni-trigram feature.

Abusive language detection in youtube comments leveraging replies as conversational context

“…we evaluated our models using Recall (R), Precision (P), and macro F1-measure. These machine and deep learning classifiers have shown competitive performance for several NLP tasks (Devlin et al, 2019;Kim, 2014;Hochreiter & Schmidhuber, 1997;Breiman, 2001;Kohavi, 1995;Bashir et al, 2019;Khan et al, 2021;Butt et al, 2021b;Karande et al, 2021;Ashraf et al, 2021;Ameer et al, 2021;Butt et al, 2021a).…”

Multi-label emotion classification of Urdu tweets

“…Therefore, a multi-label emotion dataset for Urdu is long due and needed for understanding public emotions, especially applicable in natural language applications in disaster management, public policy, commerce, and public health. It should also be noted that emotion detection directly aids in solving other text related classification tasks such as sentiment analysis ( Khan et al, 2021 ), human aggressiveness and emotion detection ( Bashir et al, 2019 ; Ameer et al, 2021 ), humor detection ( Weller & Seppi, 2019 ), question answering and fake news detection ( Butt et al, 2021a ; Ashraf et al, 2021 ), depression detection ( Mustafa et al, 2020 ), and abusive and threatening language detection ( Ashraf, Zubiaga & Gelbukh, 2021 ; Ashraf et al, 2020 ; Butt et al, 2021b ; Amjad et al, 2021 ).…”

Deep Learning Based Cross Domain Sentiment Classification for Urdu Language

“…As per existing research studies, SA can be categorized as multi-domain SA [5], [7], [8], Cross Domain Sentiment Analysis (CDSA) [9], [10], bilingual SA [11], [12], and multilingual SA [13], [14]. In multi-domain SA, the dataset is collected from multiple genres, and training and testing of models are performed on the same dataset.…”

“…In OSNs, many native Urdu speakers use different platforms like YouTube, Facebook, and Twitter to express their opinions, emotions, and feelings using Urdu script and Roman Urdu (Latin script). Consequently, it is crucial to perform SA of Urdu script to grasp the feelings, emotions, and opinions of native Urdu speakers [7]. Existing works on Urdu SA [18]- [21] rely on the availability and quality of labeled data.…”