Narratives are the cognitive and emotional scaffolds of propaganda. They organize isolated persuasive techniques into coherent stories that justify actions, attribute blame, and evoke identification with ideological camps. In this paper, we propose a novel fine-grained narrative classification in biased news article. We also explore article-bias classification as the pre-cursor task to narrative classification and fine-grained persuassive technique identification. We develop INDI-PROP, the first ideologically grounded fine-grain narrative dataset with multi-level annotation for analyzing propaganda in Indian news media. Our dataset INDI-PROP comprises 1,266 articles focusing on two polarizing socio-political events in recent times: CAA/NRC and the Farmers’ protest. Each article is annotated at three hierarchical levels: (i) ideological article-bias (pro-government, pro-opposition, neutral), (ii) event-specific fine-grained narrative frames anchored in ideological polarity and communicative intent, and (iii) persuasive techniques. We propose FANTA and TPTC, two GPT-4o guided multi-hop prompt-based reasoning frameworks for the bias, narrative, and persuasive technique classification. FANTA leverages multi-layered communicative phenomenon by integrating information extraction and contextual framing for hierarchical reasoning. On the other hand, TPTC adopts systematic decomposition of persuasive cues via a two-stage approach. Our evaluation suggest substantial improvement over underlying baselines in each case.

The application of Natural Language Processing is progressively extending into many domains as time progresses. We are motivated to evaluate language model’s (LMs) capabilities in many real-world domains due to their significant potential. This study examines the use of LMs in sports, explicitly emphasizing their ability to convert data into text and their understanding of cricket. By examining cricket scorecards, a widely played sport on the Indian subcontinent and many other regions, we will evaluate the summaries produced by LMs from several viewpoints. We have collected concise summaries of the scorecards from the ODI World Cup 2023 and assessed them in terms of both factual accuracy and sports-specific significance. We analyze the specific factors that are included in the summaries and those that are excluded. Additionally, it analyzes prevalent mistakes concerning completeness, correctness, and conciseness. We are presenting our findings here and also our dataset and code are available https://github.com/satyawork/ODI-WORLDCUP.git