SENTIMENT ANALYSIS OF ROMAN URDU REVIEWS

Abstract

Easy access and economic availability of Computers, Tabs, Smartphones and high—speed internet people are now using web for Social interaction and Business correspondence. People are becoming habitual to post their reviews about any specific entity/product, they used. These reviews are very helpful for both—user and seller. Initially these reviews not too much they can easily be analyzed by reading them. The continuous increase in the amount of these reviews creates a need that reviews can be analyzed and useful pattern be found and explored through automated channel. This need leads to a new filed in the domain of research known as “Sentiment Analysis”. Sentiment Analysis is the study of people’s opinions, sentiments, attitude and emotions expressed in written language or also said that, it is a process of categorizing people’s opinions expressed in the piece of text especially in order to determine whether the writer’s attitude towards a particular topic or product is positive, negative, or neutral. This research is targeting the mining of the sentiments from these reviews of PSL anthums. In this thesis, five different classification model are used for text classification of reviews by using Rapid Miner Tool. Thesis presents a Sentiment Analysis of Roman Urdu reviews on PSL Anthums available on YouTube. These reviews are scraped, pre—process and analysed using Naïve Bayes, Gradient Boost Tree, Support Vector Machine, K-Nearist Neighbours and Artificail Neural Netwrok. The Roman Urdu Sentiment Analysis is perform at 7000 bi-lingual reviews. The Naïve Bayes and and Logistic Regression correctly predicted 68.86% reviews. ANN achived 68.86% on testing dataset and 69.71% on the validation of the results.