Leveraging Media Frames to Improve Normative Diversity in News Recommendations

Sourabh Dattawad; Agnese Daffara; Tanise Ceron

Home/Archive/arXiv

arXiv · 2509.02266

Leveraging Media Frames to Improve Normative Diversity in News Recommendations

Sourabh Dattawad·Agnese Daffara·Tanise Ceron

View original source ↗Read source document ↗Export metadata ↓

Abstract

Click-based news recommender systems suggest users content that aligns with their existing history, limiting the diversity of articles they encounter. Recent advances in aspect-based diversification -- adding features such as sentiments or news categories (e.g. world, politics) -- have made progress toward diversifying recommendations in terms of perspectives. However, these approaches often overlook the role of news framing, which shapes how stories are told by emphasizing specific angles or interpretations. In this paper, we treat media frames as a controllable aspect within the recommendation pipeline. By selecting articles based on a diversity of frames, our approach emphasizes varied narrative angles and broadens the interpretive space recommended to users. In addition to introducing frame-based diversification method, our work is the first to assess the impact of a news recommender system that integrates frame diversity using normative diversity metrics: representation, calibration, and activation. Our experiments based on media frame diversification show an improvement in exposure to previously unclicked frames up to 50%. This is important because repeated exposure to the same frames can reinforce existing biases or narrow interpretations, whereas introducing novel frames broadens users' understanding of issues and perspectives. The method also enhances diversification across categorical and sentiment levels, thereby demonstrating that framing acts as a strong control lever for enhancing normative diversity.

Explore related subjects

cs.IR

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Sourabh Dattawad, Agnese Daffara, Tanise Ceron. 2025-09-02. Leveraging Media Frames to Improve Normative Diversity in News Recommendations. https://arxiv.org/abs/2509.02266

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data

Slate recommender systems (RecSys) present users with ordered sets of interacting items (e.g., playlists). We investigate whether large language models (LLMs) can articulate pairwise preferences between slates for synthetic A/B testing of slate RecSys. We introduce a validation protocol measuring the alignment of synthetic preferences with classical RecSys metrics and their compliance with preference axioms, and use it to characterise how LLM pre-training and configuration affect slate preference articulation. Combined with the generalized Rao-Kupper model, synthetic LLM-based A/B testing recovers rankings that remain stable across utility weightings, whereas off-policy estimators are reliable only when the target utility matches the logged behavior. We position it as a screening stage between off-policy evaluation and live experiments: not a replacement for A/B testing, but a way to reserve its cost for the most promising candidates.

cs.IR↗

arXiv2026

MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval

Existing retrieval benchmarks primarily consist of text-based queries where keyword or semantic matching is usually sufficient. Many real-world queries contain multimodal elements, particularly, images such as diagrams, charts, and screenshots that require intensive reasoning to identify relevant documents. To address this gap, we introduce MM-BRIGHT, the first multimodal benchmark for reasoning-intensive retrieval. Our dataset consists of 2,803 real-world queries spanning 29 diverse technical domains, with four tasks of increasing complexity: text-to-text, multimodal-to-text, multimodal-to-image, and multimodal-to-multimodal retrieval. Extensive evaluation reveals that state-of-the-art models struggle across all tasks: BM25 achieves only 8.5 nDCG@10 on text-only retrieval, while the best multimodal model Nomic-Vision reaches just 27.6 nDCG@10 on multimodal-to-text retrieval actually underperforming the best text-only model (DiVeR: 32.2). These results highlight substantial headroom and position MM-BRIGHT as a testbed for next-generation retrieval models that better integrate visual reasoning. Our code and data are available at https://github.com/mm-bright/MM-BRIGHT. See also our official website: https://mm-bright.github.io/.

cs.IR↗

arXiv2026

From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search

Traditional Web search follows a human-facing paradigm in which users inspect ranked documents and synthesize information themselves. In AI Search, retrieved documents instead serve as inputs to a generation model, shifting the retrieval objective from ranking documents by Search Satisfaction to constructing reliable context for correct answer generation. We formulate this shift as answer-oriented context construction through a three-stage framework: (1) Answer Support identifies candidate documents that contribute information to answer generation; (2) Content Trustworthiness assesses whether this information provides a reliable basis for correct answers from source, temporal, and factual perspectives; and (3) Context Organization selects, consolidates, and structures retained information under a finite context budget for consistent and robust generation. We further develop an industrial workflow spanning prior and posterior optimization and establish a systematic evaluation protocol covering both retrieval-side context and final answers. Experiments show consistent improvements at both Retrieval and Answer levels, demonstrating the effectiveness of the framework and its industrial implementation.

cs.IR↗