Browsing by Author "Haque, Monirul"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Analyzing and predicting trends in contemporary social discourse through hashtag campaigns
    (BRAC University, 2024-10) Muhtasim, Shihab; Siddiky, Raiyan Wasi; Sadeque, Farig Yousuf; Haque, Monirul
    In the current landscape of social media, hashtags play a significant observable role in boosting the movement of information across a diverse range of fields and people. This research aims to identify and then examine extremely popular hashtags on social media and uncover the characteristics that make these hashtags popular. It attempts to follow the hashtag along its journey over time in gaining and losing popularity and in doing so, extrapolates to analyze the boom of past trends over time and the impact that hashtags have in propagating information. The research further tries to create a structure for a network showcasing the propagation of information and interaction between users as they engage using the hashtag in an attempt to understand why and how these hashtags reach such a diversified range of groups and people. It also attempts to be able to predict and forecast the trend and direction of the hashtag and the interaction it generates after the interaction period. Using a mixture of modern techniques such as network science and graph theory concepts, unsupervised machine learning tools, greedy modularity maximization model, and many other natural language processing (NLP) tools such as LSTM, there is the potential to understand the influence of popularity through hashtags and be able to predict the popularity of hashtags.
  • Thumbnail Image
    Item
    BanglaBait: using transformers, neural networks & statistical classifiers to detect clickbaits in New Bangla Clickbait Dataset
    (BRAC University, 2022-01) Mahtab, Motahar; Haque, Monirul; Hasan, Mehedi; Akon, Mujtahid Al-Islam; Mostakim, Moin
    The art of luring us to click on certain content by exploiting our curiosity is recognized as clickbait. Clickbait might be aggravating at times because it is misleading. Several studies have worked on the detection of clickbait in online platforms as we transition from the Information Age to the Age of AI. Nonetheless, predicting clickbait in Bengali new articles is still a work in progress. Here, we use deep learning, the process of extracting pattern or feature from data using neural networks, to determine whether an online Bengali article is clickbait or not. We scrape data from online Bengali news articles, manually annotate them and employ deep nerural network architectures like CNN, Bi-LSTM,Bi-GRU and pre-trained fine-tuning language representation approaches –i.e. BERT, BanglaBERT, M-BERT to provide inputs for various types of classifiers. Finally, we evaluate the classifiers’ outputs and choose the best outcome to predict clickbait in Bengali news articles.