Deep sentiments in Roman Urdu text using Recurrent Convolutional Neural Network model

Most existing studies are focused on popular languages like English, Spanish, Chinese, Japanese, and others, however, limited attention has been paid to Urdu despite having more than 60 million native speakers. In this paper, we develop a deep learning model for the sentiments expressed in this under-resourced language. We develop an open-source corpus of 10,008 reviews from 566 online threads on the topics of sports, food, software, politics, and entertainment. The objectives of this work are bifold (a) the creation of a human-annotated corpus for the research of sentiment analysis in Urdu; and (b) measurement of up-to-date model performance using a corpus. For their assessment, we performed binary and ternary classification studies utilizing another model, namely long short-term memory (LSTM), recurrent convolutional neural network (RCNN) Rule-Based, N-gram, support vector machine , convolutional neural network, and LSTM. The RCNN model surpasses standard models with 84.98% accuracy for binary classification and 68.56% accuracy for ternary classification. To facilitate other researchers working in the same domain, we have open-sourced the corpus and code developed for this research.

show abstract

“…Researchers have also attempted to establish corpora and methods for Urdu sentiment analysis (Mahmood et al, 2020;.…”

Section: Sentiment Analysis For Urdumentioning

confidence: 99%

Sentiment analysis for Urdu online reviews using deep learning models

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithm such as RCNN has also been used for the sentiment Analysis. Zainabat al [7] conducted a study to evaluate the sentiment of Roman-Urdu text using Rule-based, Ngram with Recurrent Convolutional Neural Network. They used a huge dataset of more than 10,000 sentences.…”

Section: Classificationmentioning

confidence: 99%

Sentiment Analysis of Roman-Urdu Tweets about Covid-19 Using Machine Learning Approach: A Systematic Literature Review

2021

IJATCSE

View full text Add to dashboard Cite

From the past decade, growth of social media encourages researchers to perform several academic studies on the user generated data. Sentiment Analysis is tool used to generate summary of public opinion about a topic, which helps in effective decision making. Most of the work in sentiment analysis has been performed on English Language Dataset. Many Languages such as Urdu, Hindi, and Italian faced lack of attention due to their complex morphological structure and unavailability of resources. COVID-19 has affected human life around the world. Many researchers have performed their studies using twitter data for knowing the sentiments of people throughout the time of pandemic. In this Paper we are giving a general overview about the process of Sentiment Analysis of Roman-Urdu Tweets. For the dataset query we have used the data generated by user about COVID19.

show abstract

“…The words of a given sentence or document are looked up in the lexicon and the individual weights are accumulated and compared against the defined threshold to output the final 'positive', 'negative' or 'neutral' label. The most commonly used lexical method for sentiment analysis of English data is Valence Aware Dictionary for sEntiment Reasoning (VADER) [5].The problem with the lexical methods is that they are unable to capture the underlying semantics in most of the cases since they only rely on the presence or absence of extreme words, which deems unsatisfactory results [6].…”

Section: Introductionmentioning

confidence: 99%

Improving Hate Speech Detection of Urdu Tweets Using Sentiment Analysis

et al. 2021

View full text Add to dashboard Cite

Sentiment Analysis is a technique that is being used abundantly nowadays for customer reviews analysis, popularity analysis of electoral candidates, hate speech detection and similar applications. Sentiment analysis on tweets encounters challenges such as highly skewed classes, high dimensional feature vectors and highly sparse data. In this study, we have analyzed the improvement achieved by successively addressing these problems in order to determine their severity for sentiment analysis of tweets. Firstly, we prepared a comprehensive data set consisting of Urdu Tweets for sentiment analysis-based hate speech detection. To improve the performance of the sentiment classifier, we employed dynamic stop words filtering, Variable Global Feature Selection Scheme (VGFSS) and Synthetic Minority Optimization Technique (SMOTE) to handle the sparsity, dimensionality and class imbalance problems respectively. We used two machine learning algorithms i.e., Support Vector Machines (SVM) and Multinomial Naïve Bayes' (MNB) for investigating performance in our experiments. Our results show that addressing class skew along with alleviating the high dimensionality problem brings about the maximum improvement in the overall performance of the sentiment analysis-based hate speech detection.

show abstract

Deep sentiments in Roman Urdu text using Recurrent Convolutional Neural Network model

Cited by 68 publications

References 38 publications

Sentiment analysis for Urdu online reviews using deep learning models

Sentiment analysis for Urdu online reviews using deep learning models

Sentiment Analysis of Roman-Urdu Tweets about Covid-19 Using Machine Learning Approach: A Systematic Literature Review

Improving Hate Speech Detection of Urdu Tweets Using Sentiment Analysis

Contact Info

Product

Resources

About