RUSAS: Roman Urdu Sentiment Analysis System

作     者：Kazim Jawad Muhammad Ahmad Majdah Alvi Muhammad Bux Alvi 

作者机构：Faculty of Computer Science and EngineeringFrankfurt University of Applied SciencesFrankfurt am Main60318Germany Technical Writer and ResearcherProteus Technologies LLCIslamabad04405Pakistan Faculty of EngineeringThe Islamia University of BahawalpurBahawalpur63100Pakistan 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第79卷第4期

页      面：1463-1480页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors received no specific funding for this study 

主　　题：Roman Urdu sentiment analysis Roman Urdu language detector Roman Urdu spelling checker flask 

摘      要：Sentiment analysis, the meta field of Natural Language Processing (NLP), attempts to analyze and identify thesentiments in the opinionated text data. People share their judgments, reactions, and feedback on the internetusing various languages. Urdu is one of them, and it is frequently used worldwide. Urdu-speaking people prefer tocommunicate on social media in Roman Urdu (RU), an English scripting style with the Urdu language *** have developed versatile lexical resources for features-rich comprehensive languages, but limitedlinguistic resources are available to facilitate the sentiment classification of Roman Urdu. This effort encompassesextracting subjective expressions in Roman Urdu and determining the implied opinionated text polarity. Theprimary sources of the dataset are Daraz (an e-commerce platform), Google Maps, and the manual effort. Thecontributions of this study include a Bilingual Roman Urdu Language Detector (BRULD) and a Roman UrduSpelling Checker (RUSC). These integrated modules accept the user input, detect the text language, correct thespellings, categorize the sentiments, and return the input sentence’s orientation with a sentiment intensity *** developed system gains strength with each input experience gradually. The results show that the languagedetector gives an accuracy of 97.1% on a close domain dataset, with an overall sentiment classification accuracy of94.3%.