Sentiment Analysis for Roman Urdu

Abstract

The majority of online comments/opinions are written in text-free format. Sentiment Analysis can be used as a measure to express the polarity (positive/negative) of comments/opinions. These comments/ opinions can be in different languages i.e. English, Urdu, Roman Urdu, Hindi, Arabic etc. Mostly, people have worked on the sentiment analysis of the English language. Very limited research work has been done in Urdu or Roman Urdu languages. Whereas, Hindi/Urdu is the third largest language in the world. In this paper, we focus on the sentiment analysis of comments/opinions in Roman Urdu. There is no publicly available Roman Urdu public opinion dataset. We prepare a dataset by taking comments/opinions of people in Roman Urdu from different websites. Three supervised machine learning algorithms namely NB (Naive Bayes), LRSGD (Logistic Regression with Stochastic Gradient Descent) and SVM (Support Vector Machine) have been applied on this dataset. From results of experiments, it can be concluded that SVM performs better than NB and LRSGD in terms of accuracy. In case of SVM, an accuracy of 87.22% is achieved.

Multi-text classification of Urdu/Roman using machine learning and natural language preprocessing techniques

“…Starting from simple features then moved to their eight features set. It was concluded that these set of eight features have been used in text sentiment analysis for English language (13) .…”

“…min_df : It is the minimum numbers of documents a word must be present in to be kept. Nor m: It is set to l2; to ensure all our feature vectors have a euclidian norm of 1. ngram_range: It is set to (1,2) to indicate that we want to consider both unigrams and bigrams. stop_words: It is set to "preprocessing variable (Which holds all the necessary stopwords for Urdu and Roman Urdu Language)" to remove all common pronouns ("a", "the", etc) to reduce the number of noisy features.…”

“…For example various news, articles, stories, blogs and reviews text content typically organized by topics and different products tagged by categories and users can be classified on the basis on how they talk about particular brand or product on online web based platforms However, the majority of text classification blogs and tutorials on the internet can be found in the form of binary text classification whose common example include email classification such as email spam filtering (spam vs. ham), sentiment analysis (positive vs. negative) respectively. The Research has also identified the problem with two Roman Urdu words have same spelling but lexically they are different from each other such as common and mango spelled aam in Roman Urdu, but for quality training of model words need to maintain consistency in its use throughout the process (1,2) . For the analysis of textual data category, the most common and useful approach which plays an important role in the field of NLP like opinion mining, sentiment analysis, tweets, reviews, spam detection, email filtering is the common example of text categorization (3) .…”

Recognition and Effective Handling of Negations in Enhancing the Accuracy of Urdu Sentiment Analyzer

“…Most of the researchers have worked on SA using languages other than Urdu. Few researchers have worked in Urdu SA [21]. Urdu corpus and lexicon are developed by researchers [22][23][24][25].…”

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

“…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.…”