Sentiment analysis plays a pivotal role in understanding public opinion, particularly in the political domain where the portrayal of entities in news articles influences public perception. In this paper, we investigate the effectiveness of Large Language Models (LLMs) in predicting entity-specific sentiment from political news articles. Leveraging zero-shot and few-shot strategies, we explore the capability of LLMs to discern sentiment towards political entities in news content. Employing a chain-of-thought (COT) approach augmented with rationale in few-shot in-context learning, we assess whether this method enhances sentiment prediction accuracy. Our evaluation on sentiment-labeled datasets demonstrates that LLMs, outperform fine-tuned BERT models in capturing entity-specific sentiment. We find that learning in-context significantly improves model performance, while the self-consistency mechanism enhances consistency in sentiment prediction. Despite the promising results, we observe inconsistencies in the effectiveness of the COT prompting method. Overall, our findings underscore the potential of LLMs in entity-centric sentiment analysis within the political news domain and highlight the importance of suitable prompting strategies and model architectures.

Alapan Kuila Sudeshna Sarkar

Navigating the complex landscape of news articles involves understanding the various actors or entities involved, referred to as news stakeholders. These stakeholders, ranging from policymakers to opposition figures, citizens, and more, play pivotal roles in shaping news narratives. Recognizing their stakeholder types, reflecting their roles, political alignments, social standing, and more, is paramount for a nuanced comprehension of news content. Despite existing works focusing on salient entity extraction, coverage variations, and political affiliations through social media data, the automated detection of stakeholder roles within news content remains an underexplored domain. In this paper, we bridge this gap by introducing an effective approach to classify stakeholder types in news articles. Our method involves transforming the stakeholder classification problem into a natural language inference task, utilizing contextual information from news articles and external knowledge to enhance the accuracy of stakeholder type detection. Moreover, our proposed model showcases efficacy in zero-shot settings, further extending its applicability to diverse news contexts.

Alapan Kuila Sudeshna Sarkar

The determination of Lande's g-factor and the damping constant is central to extracting crucial information about the spin-spin and spin-orbit interactions in magnetically ordered systems. In insulating compounds based on 3d elements, the spin-orbit interaction can be effectively probed by investigating the ground state of the corresponding free 3d ion within the crystalline environment. For metallic systems, the problem is non-trivial because of additional band structure effects. Here, we investigate the anisotropic magnetization dynamics in bulk single crystalline Fe5GeTe2, a van der Waals 2D itinerant ferromagnet at room temperature, using broadband ferromagnetic resonance spectroscopy. Strikingly, contrary to the results of ab-initio calculations, we do not observe any intrinsic anisotropy of magnetization damping close to room temperature, suggesting diminished role of spin-orbit interaction. However, there is a sizable anisotropy in the Lande's g factor near room temperature which is attributed to anisotropic critical spin fluctuations.

Alapan Bera Nirmalya Jana Amit Agarwal Soumik Mukhopadhyay

Iron-based van der Waals (vdW) ferromagnets with relatively high ordering temperatures are a current research focus due to their significance in fundamental physics and potential applications in spintronics. Competing magnetic interactions and anisotropies can give rise to nontrivial spin textures in these materials, resulting in novel topological features. Fe4GeTe2 (F4GT) is a nearly room-temperature vdW ferromagnet, well known for hosting a spin-reorientation transition (SRT) arising from the interplay of perpendicular magnetic anisotropy (PMA) and shape anisotropy. In this work, we investigate the angle-dependent magneto-transport properties of F4GT single crystals. We report a large topological Hall effect (THE) in a multi-layer F4GT originating from the SRT-driven non-coplanar spin textures. The THE appears at the in-plane orientation of the external magnetic field and persists over a wide range of temperatures around SRT. Additionally, we find a thickness-sensitive THE signal for the c axis orientation of the magnetic field at a low-temperature regime which is associated with a reentrant Lifshitz transition.

Alapan Bera Soumik Mukhopadhyay

Static magnetic dipole solutions of Einstein-Maxwell equations from the soliton solutions of a Kerr object

Avinanda Chaudhuri S Nandi S Chaudhuri

Let $X$ be a surface and let $L$ be an ample line bundle on $X$. We first obtain a lower bound for the Seshadri constant $\varepsilon(X,L,r)$, when $r \ge 3$. We then assume that $X$ is a ruled surface and study Seshadri constants on $X$ in greater detail. We also make precise computations of Seshadri constants on $X$ in some cases.

Krishna Hanumanthu Alapan Mukhopadhyay

The coverage of different stakeholders mentioned in the news articles significantly impacts the slant or polarity detection of the concerned news publishers. For instance, the pro-government media outlets would give more coverage to the government stakeholders to increase their accessibility to the news audiences. In contrast, the anti-government news agencies would focus more on the views of the opponent stakeholders to inform the readers about the shortcomings of government policies. In this paper, we address the problem of stakeholder extraction from news articles and thereby determine the inherent bias present in news reporting. Identifying potential stakeholders in multi-topic news scenarios is challenging because each news topic has different stakeholders. The research presented in this paper utilizes both contextual information and external knowledge to identify the topic-specific stakeholders from news articles. We also apply a sequential incremental clustering algorithm to group the entities with similar stakeholder types. We carried out all our experiments on news articles on four Indian government policies published by numerous national and international news agencies. We also further generalize our system, and the experimental results show that the proposed model can be extended to other news topics.

Alapan Kuila Sudeshna Sarkar

Let $k$ be an arbitrary field. We construct examples of regular local $k$-algebras $R$ (of positive dimension) for which the ring of differential operators $D_k(R)$ is trivial in the sense that it contains {\it no} operators of positive order. The examples are excellent in characteristic zero but not in positive characteristic. These rings can be viewed as being non-singular but they are not simple as $D$-modules, laying to rest speculation that $D$-simplicity might characterize a nice class of singularities in general. In prime characteristic, the construction also provides examples of {\it regular} local rings $R$ (with fraction field a function field) whose Frobenius push-forward $F_*^eR$ is {\it indecomposable} as an $R$-module for all $e\in \mathbb N$. Along the way, we investigate hypotheses on a local ring $(R, m)$ under which $D$-simplicity for $R$ is equivalent to $D$-simplicity for its $m$-adic completion, and give examples of rings for which the differential operators do not behave well under completion. We also generalize a characterization of $D$-simplicity due to Jeffries in the $\mathbb N$-graded case: for a Noetherian local $k$-algebra $(R, m, k)$, $D$-simplicity of $R$ is equivalent to surjectivity of the natural map $D_k(R)\to D_k(R, k)$.

Alapan Mukhopadhyay Karen E. Smith

See hep-th/9907179.

Shyamoli Chaudhuri

In this note we show that $k$-convex functions on $\Bbb R^n$ are twice differentiable almost everywhere for every positive integer $k>n/2$. This generalizes the classical Alexsandrov's theorem for convex functions.

Nirmalendu Chaudhuri Neil S. Trudinger