Author Profiling from Short Romanized Urdu Messages: A Preliminary Investigation using Transfer Learning Models
DOI:
https://doi.org/10.21015/vtse.v11i3.1615Abstract
Author profiling, a crucial task in natural language processing, involves identifying various attributes of an author, such as gender and age, from text. This study examines how transfer learning models in the context of author profiling from Roman Urdu text. We conduct experiments employing prominent models such as ELECTRA , BERT, RoBERTa, XLNet, Distil Bert, Distil RoBERTa,. Our analysis reveals superior performance in gender prediction using BERT, attaining an accuracy of 0.74698, precision of 0.7505, recall of 0.7462, and F1 score of 0.7456. On the other hand, RoBERTa demonstrates remarkable proficiency in age prediction with an accuracy of 0.8221, precision of 0.8215, recall of 0.8221, and F1 score of 0.8215. These findings showcase the effectiveness of transfer learning models in author profiling tasks offer insightful analysis for further research and applications in this domain.
Author Biographies
Abid Ali, Department of Computer Software Engineering, University of Engineering & Technology Mardan, Mardan 23200 Pakistan
Abid, an IT graduate and professional Software Engineer specializing in Unity Game Development and Mobile App Development. With expertise in Java, C#, Kotlin, Dart and Python, he excels in creating high-quality Mobile Games and Apps with exceptional performance, prioritizing performance and quality. He consistently delivers top-notch products within deadlines. Currently pursuing a Master's degree in Computer Software Engineering from University of Engineering & Technology, Marden, Pakistan, focusing on NLP and Deep Learning, He applies cutting-edge techniques to enhance Games and App development capabilities. With proficiency in Java, C#, Kotlin, Dart and Python, alongside his Unity Game Development skills and ongoing studies, He strives to deliver outstanding software solutions. His goal is to develop engaging and high-performance Games and Apps while utilizing innovative technologies to optimize business processes. He places a strong emphasis on quality, performance, and user experience, aiming to exceed client expectations and contribute to the advancement of the software development industry.
Muhammad Sohail Khan, Department of Computer Software Engineering, University of Engineering & Technology Mardan, Mardan 23200 Pakistan
Muhammad Sohail Khan received the M.S. degree from the Computer Software Engineering Department, University of Engineering & Technology Peshawar, in 2012, and the Ph.D. degree from Jeju National University, South Korea, in 2016. He is currently an Assistant Professor with the Department of Computer Software Engineering, University of Engineering & Technology Mardan, Pakistan. He had been a part of the software development industry in Pakistan as a designer and a developer. The major focus of his work is the investigation and application of alternate programming strategies to enable the involvement of masses in the Internet of Things application design and development. His research interests include the IoT, blockchain, cloud computing, machine learning, end-user programming, human–computer interactions, and empirical software engineering.
Muhammad Amin Khan, Department of Computer Science, CECOS University of IT and Emerging Sciences, Peshawar, Pakistan
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-By) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution License CC BY
