publications

2022

1. 

   Hostility Detection in Online Hindi-English Code-Mixed Conversations

   Aditi Bagora, Kamal Shrestha, Kaushal Maurya, and 1 more author

   WebSci ’22: 14th ACM Web Science Conference 2022, Jun 2022

   Abs HTML PDF Code

   With the rise in accessibility and popularity of various social media platforms, people have started expressing and communicating their ideas, opinions, and interests online. While these platforms are active sources of entertainment and idea-sharing, they also attract hostile and offensive content equally. Identification of hostile posts is an essential and challenging task. In particular, Hindi-English Code-Mixed online posts of conversational nature (which have a hierarchy of posts, comments, and replies) have escalated the challenges. There are two major challenges: (1) the complex structure of Code-Mixed text and (2) filtering the relevant previous context for a given utterance. To overcome these challenges, in this paper, we propose a novel hierarchical neural network architecture to identify hostile posts/comments/replies in online Hindi-English Code-Mixed conversations. We leverage large multilingual pre-trained (mLPT) models like mBERT, XLMR, and MuRIL. The mLPT models provide a rich representation of code-mix text and hierarchical modeling leads to a natural abstraction and selection of the relevant context. The propose model consistently outperformed all the baselines and emerged as a state-of-the-art performing model. We conducted multiple analyses and ablation studies to prove the robustness of the proposed model.

2. 

   Implementation of Machine Learning Approach to Detect Clickbaits in Online News

   Prajwol Lamichhane, and Kamal Shrestha

   Fuse Machines Inc, Company Journal, 2022, May 2022

   Abs HTML PDF

   Citizen Journalism has boomed the opportunities for content marketing and public opinion. It is a golden rule of journalism, taught to any news reporter at the beginning of their career-your introduction should grab the reader straight away. Almost all of the online news media outlets completely depend upon the revenues generated from the clicks made by their readers,and due to the presence of numerous such outlets, they need to compete with each other for reader attention. So, In order to attract the readers to click on an article and subsequently visit the media site, the outlets often come up with catchy headlines accompanying the article links, which lure the readers to click on the link. Such headlines are known as Clickbaits. While these baits may trick the readers into clicking, in the long run, clickbaits usually don’t live up to the expectation of the readers, and leave them disappointed. In this work, we attempt to detect clickbaits based on features extracted from the headline of the news and then classify it accordingly. We were able to run a number of extensive cross checking to different news headlines from multiple platforms and were able to obtain an accuracy of 79% in detecting clickbait headlines.

2021

2020

1. 

   A Machine Learning Approach to Identify Fake News

   K. Shrestha, Prakash Poudyal, and Ranabhatand Diwash (2022) Karki

   Center for Project Management and Information Systems (PMIS) Review, 2022, May 2020

   Abs HTML PDF

   The information age has created several outlets to pave the pathway for public opinion and citizen journalism. With an exponential number of contents being created on a daily basis, a significant part of it includes fake content, or so-called “fake news”, usually created with malicious intent. Such an alarming growth of fake news, malicious lies, ineffectiveness of fact-checking and resilience of populist propaganda, demands a system that classifies it to prevent public deceiving and maintain ethical journalism. A promising solution that has come up recently is to use machine learning algorithms to detect patterns in the circulated news that will aid in filtering out the fake content. On this note, we have developed a classification model using the lexical and semantic features extracted from news articles and its sources. Naive Bayes, Support Vector Machine, Logistic Regression, and k-NN models were used and the results were compared to determine the best one among them. Based on precision, recall and f1 score, k-NN and Logistic Regression gave the most promising results. This is quite inspiring and significant to what was previously developed with similar techniques.