Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Phadatare, A.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Multimodal Meme Troll and Domain Classification Using Contrastive Learning
    (Institute of Electrical and Electronics Engineers Inc., 2024) Phadatare, A.; Jayanth, P.; Anand Kumar, M.A.
    This paper presents a holistic approach to meme trolling detection and domain classification, focusing on Telugu and Kannada languages. Leveraging a spectrum of methodologies ranging from basic machine learning models such as Support Vector Machines (SVM), Random Forest, Naive Bayes, to image-based models like Convolutional Neural Networks (CNN), ResNet-50, and state-of-the-art models such as CLIP, multilingual BERT, XLM-BERT, and Vision Transformers, we explore diverse modalities including image classification, extracted text classification, and combined text-caption classification. Our system integrates multiple models to achieve two primary goals: accurately detecting trolling behavior and classifying memes into thematic domains like politics, movies, sports.. By training on multilingual data and considering linguistic diversity, our approach ensures robust performance across different linguistic contexts, providing valuable insights into meme culture and trolling behavior in Telugu and Kannada-speaking communities. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Enhanced Conditional Random Field Models for Cause and Effect Detection in Financial Documents
    (Institute of Electrical and Electronics Engineers Inc., 2024) Agrawal, S.; Phadatare, A.; Anand Kumar, M.
    This paper addresses the Financial Document Causality Detection Task (FinCausal-2023), aiming to uncover the intricate causal relationships embedded in financial texts. The methodology proposed incorporates diverse natural language processing techniques, including Word2Vec embeddings, BERT embeddings, contextual encoding with BERT, token classification using SVM, and Conditional Random Fields (CRF). The study proposes a novel method to enhance the performance of CRFs using features created from a contextual based classification model and compares the same with the SOTA methods. Evaluation metrics, including precision, recall, F1-score, and an exact match percentage, assess the effectiveness of the proposed methodologies.The literature review section provides insights into previous work in financial causality detection, covering shared tasks, and models such as sequence labeling, etc. The paper concludes with results presented and a discussion of their implications, contributing to the ongoing discourse on causality detection in financial narratives. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Multi-level Attention driven GAT for recommending top profitable stocks and sectors
    (Institute of Electrical and Electronics Engineers Inc., 2025) Phadatare, A.; Patel, M.M.; Mohan, B.R.; Chaithra
    Financial technology has drawn significant attention from investors and companies. Recently there is growing demand in use of graph networks for time series data. While traditional stock analysis primarily focuses on predicting stock prices, there is comparatively less emphasis on recommending profitable stocks. Neglecting relationships between stocks and sectors can miss crucial shared information. In this work, we aim to recommend the top profitable stocks and sectors, utilizing time series data of stock prices and sector information. We introduce a novel deep learning-based model, Multilevel-Attention based Graph Attention Network designed to incorporate relationship between both stocks and sectors and rank them. First, we created a dataset for Indian stock market of NIFTY50 companies. Second, we used LSTM to create embedding and constructed fully connected graphs for stocks and sectors, and then using graph attention networks to learn latent interactions among them. Lastly, we used Multi-level and Hierarchical attention networks to rank the stocks and sectors. Comparing our multi-level attention approach to an approach with the absence of multi-level attention, the mean F1 score increased from 0.256 to 0.309, showing an improvement of 20.84%. Similarly, mean accuracy score increased from 0.251 to 0.388, showing an improvement of 54.40%. The implication of our research is varied as it can be applied in numerous scenarios like forecasting, helping in managing portfolios and assessing risks by analyzing trends and patterns of stocks. © 2025 IEEE.