newsroom data teams

Abstract: Communicating uncertainty is increasingly recognized as important in data journalism, yet in practice it is often oversimplified, downplayed, or omitted. To understand how uncertainty is handled in newsroom visualization practice, we conducted a full-day workshop with 11 data journalists from major German-speaking newsrooms. The workshop combined presentations of newsroom examples, collaborative scenario classification, World Café discussions on authoring hurdles, and group reflections on audience needs and future directions. Our findings suggest that uncertainty communication is primarily a workflow- and context-dependent editorial decision, constrained by production overhead, anticipated audience misinterpretation, publication formats, and the need to preserve a clear takeaway. Rather than relying on advanced visualization techniques, practitioners favor pragmatic defaults, layered communication, and explanatory guidance tailored to audience and medium. The scenario-based framework we provided is valued less as a strict taxonomy for classifying finished visualizations than as a planning prompt for early design reasoning. Based on these insights, we contribute (i) practitioner-informed findings on the challenges and strategies of visualizing uncertainty in journalistic practice, (ii) a refined scenario-based framework to support communication about uncertainty, and (iii) practice-oriented heuristics for designing uncertainty visualizations in newsrooms. Our work contributes to bridging visualization research and newsroom practice by grounding uncertainty communication in the realities of journalistic production. Supplemental material is available at https://osf.io/8j4ep.

Abstract: Computational framing analysis is dominated by supervised classifiers that require large annotated corpora and predefined frame taxonomies, limiting their use for non-English languages, novel events, and low-resource settings. This paper presents Association Rule Mining (ARM) as an unsupervised, annotation-free framework for news framing detection. Each document or sentence is treated as a transaction of lexical items, and high-lift co-occurrence rules are read as candidate framing signals (Gamson and Modigliani's condensing symbols), confirmed in context by journalist-researchers. The primary validation is Framing Gaza: 25,512 English-language articles from 16 US, UK, French, and German outlets covering the first year of the Gaza war (October 2023 to October 2024), analyzed with Apriori (mlxtend), platform-weighted support, POS-filtered n-grams, and lift-based scoring. ARM inductively surfaces interpretable patterns without predefined categories: a cross-platform military frame, {israeli, strike} to {kill}, appears as a closed rule in 14 of 16 outlets, and a month-by-month analysis recovers event-driven framing pivots (e.g., the April 2024 World Central Kitchen strike) with no prior event labeling. A systematic headline-body divergence is identified, with headlines carrying concentrated, high-lift editorial framing and body text reproducing institutional, procedural language. A methodological validation on the Seven Days project (1,575 Arabic articles on the 2026 Iran war) shows that FP-Growth enables sentence-level analysis with far lower memory overhead. Findings were validated through editorial uptake: two published investigative stories (Daraj Media; Saheeh Masr). Preprocessing code is released openly; the full pipeline is documented but withheld to preserve operational deployability.

Abstract: Data journalism, the practice of using data analysis to surface newsworthy stories, depends increasingly on the ability of reporters and investigative journalists to uncover trends, disparities, and accountability narratives. In practice, exploring large structured datasets remains slow and brittle: journalists must navigate hundreds of variables across many datasets over years, understand data coding conventions, and write non-trivial analysis code while hypotheses evolve. Although LLMs are often touted as "ask in English, get SQL/answers," real newsroom workflows expose recurring failures, e.g., schema mismatches and drift, misread domain semantics and units, and silent assumptions. We present DataWeave, a system that addresses these needs by combining conversational interaction, schema grounding, analytical planning, and executable query generation to support exploratory analysis over structured data. Rather than treating LLMs as autonomous answer engines, DataWeave frames them as interactive partners whose outputs can be inspected, corrected, and steered as hypotheses shift. We present a case study with professional journalists using our system to analyze the U.S. Department of Education's Integrated Postsecondary Education Data System (IPEDS), a high-stakes public dataset with substantial domain semantics and frequent schema updates. We also report how deployment experience and iterative refinement shaped the current DataWeave architecture and its analytical workflow. Our findings distill design principles and deployment lessons for trustworthy human-LLM collaboration in structured data analysis.