Large language models (LLMs) are increasingly used to make sense of unstructured data, but their use in contexts like conversation analysis, where sensemaking is often human-driven, iterative, and subjective, is underexplored. We introduce Forage, a retrieval-augmented generation (RAG) tool for making sense of conversation data through exploratory search. We report on user studies with 27 participants across four user groups—including NPR journalists and municipal staff—observing how Forage is used to explore and analyze conversation data. We find Forage supports insight confirmation and generation, providing structure and novel insight about search results compared to a non-LLM-enabled search tool. Driven by the goal of generating multiple perspectives in Forage, we present Wild Forage, a design provocation that generates and presents multiple interpretations of the same data along a specified axis of potential interpretive difference, like political orientation. Expert user studies show that exposure to other interpretations through Wild Forage can help users meaningfully consider their assumptions in sensemaking, but findings also highlight the importance of future work to leverage this opportunity while avoiding potential harms, like stereotyping.

Floods are disastrous events as they induce fatalities, damages to the environment, properties and infrastructure, at a global level. The Region of Attica, that hosts Athens (capital of Greece), has suffered various floods, including the severe flood in Mandra (2017) with 24 fatalities. In 2021, a Programming Agreement was signed between the Prefecture of Attica and the National Observatory of Athens to conduct the research study «Earthquake, fire and flood risk assessment in the Region of Attica» (Part A) in selected and most vulnerable areas. In the framework of this research and technical work, state-of-the-art methodologies were developed and implemented that support multi-parameter flood risk assessment and management planning at high spatial resolution (building block level). This work integrates different data sources, including remote sensing, in-situ measurements, field visits, and simulations, and is characterized by considerable added value, as it supports public actors and stakeholders in decision-making and management of disastrous events.

Community organizations face challenges in harnessing the power of qualitative data analysis, or sensemaking, to understand the diverse perspectives and needs brought up by their constituents. One of the most time-consuming and tedious parts of sensemaking is qualitative coding, or the process of identifying themes across a large and unstructured corpus of community input. A challenge in qualitative coding is attaining high intercoder reliability, especially between expert and beginner sensemakers. In this work, we present SenseMate, a novel human-AI system designed to help with qualitative coding. SenseMate leverages rationale extraction models, a new machine learning strategy to semi-automate sensemaking, which produces theme recommendations and human-interpretable explanations. The models were trained on a dataset of people’s experiences living in Boston, which was annotated for themes by expert sensemakers. We integrated rationale extraction models into SenseMate through an iterative, human-centered design process revolving around four key design principles derived from an extensive literature review. The design process consisted of three iterations with continuous feedback from seven people associated with community organizations. Through an online experiment involving 180 novice sensemakers, we aimed to determine whether AI-generated recommendations and rationales would decrease coding time, increase intercoder reliability (i.e. Cohen’s kappa), and minimize differences between novice and expert coding decisions (i.e. F-score of participant answers compared to expert gold labels). We found that though the model recommendations and explanations increased coding time by 49 seconds per unit of analysis, they raised intercoder reliability by 29% and coding F-score by 10%. Regarding the effectiveness of SenseMate’s design, participants reported that the platform was generally easy to use. In summary, Sensemate is (1) built for beginner sensemakers without a technical background, a user group that prior work doesn’t focus on, (2) implements rationale extraction models to recommend themes and generate explanations, which has advantages over large language models in terms of user privacy and control, and (3) contains original and intuitive features created from user feedback that can be applied to future QDA systems.