Lexical Variation and Sentiment Analysis of Roman Urdu Sentences with Deep Neural Networks

Abstract

Sentiment analysis is the computational study of reviews, emotions, and sentiments expressed in the text. In the past several years, sentimental analysis has attracted many concerns from industry and academia. Deep neural networks have achieved significant results in sentiment analysis. Current methods mainly focus on the English language, but for minority languages, such as Roman Urdu that has more complex syntax and numerous lexical variations, few research is carried out on it. In this paper, for sentiment analysis of Roman Urdu, the novel "Self-attention Bidirectional LSTM (SA-BiLSTM)" network is proposed to deal with the sentence structure and inconsistent manner of text representation. This network addresses the limitation of the unidirectional nature of the conventional architecture. In SA-BiLSTM, Self-Attention takes charge of the complex formation by correlating the whole sentence, and BiLSTM extracts context representations to tackle the lexical variation of attended embedding in preceding and succeeding directions. Besides, to measure and compare the performance of SA-BiLSTM model, we preprocessed and normalized the Roman Urdu sentences. Due to the efficient design of SA-BiLSTM, it can use fewer computation resources and yield a high accuracy of 68.4% and 69.3% on preprocessed and normalized datasets, respectively, which indicate that SA-BiLSTM can achieve better efficiency as compared with other state-of-the-art deep architectures.

Sentiment Analysis of Roman Text: Challenges, Opportunities, and Future Directions

“…The proposed SA-BiLSTM model leveraged self-attention and a Bidirectional LSTM network to achieve improved results. The SA-BiLSTM model attained high accuracy rates of 68.4% and 69.3% for the preprocessed and normalized datasets, respectively [48].…”

BERT-Based Sentiment Analysis for Low-Resourced Languages: A Case Study of Urdu Language

“…Manzoor et al [13] proposed a Self-attention Bidirectional LSTM (SA-BiLSTM) approach to deal with varying patterns of text representation, achieving an accuracy of 68.4% and 69.3%. Khan et al [38] created a dataset for Urdu sentiment analysis and compared various machine learning and deep learning algorithms, achieving an accuracy rate of 81.94%.…”

“…Feature engineering techniques, including n-grams, lexical features, and sentiment lexicons, have been employed to capture the linguistic characteristics of Urdu text. Additionally, researchers have also explored deep learning models [13], [14], i.e., Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs), to capture the contextual information and semantic relationships in Urdu text.…”