This paper explores the development and application of an automated system designed to extract information from semi-structured interview transcripts. Given the labor-intensive nature of traditional qualitative analysis methods, such as coding, there exists a significant demand for tools that can facilitate the analysis process. Our research investigates various topic modeling techniques and concludes that the best model for analyzing interview texts is a combination of BERT embeddings and HDBSCAN clustering. We present a user-friendly software prototype that enables researchers, including those without programming skills, to efficiently process Figure 1: The coding process visualized and visualize the thematic structure of interview data. This tool not only facilitates the initial stages of qualitative analysis but also offers insights into the interconnectedness of topics revealed, thereby unwittingly faces the problem of interpretational objectivity, and enhancing the depth of qualitative analysis.

When Ty landed an introductory phone interview with a finance and banking company last month, they assumed it would be a quick chat with a recruiter. And when they got on the phone, Ty assumed the recruiter, who introduced herself as Jaime, was human. "The voice sounded similar to Siri," said Ty, who is 29 and lives in the DC metro area. Ty realized they weren't speaking to a living, breathing person. Their interviewer was an AI system, and one with a rather rude habit.

Recent work arXiv.2310.02238 asserted that "we effectively erase the model's ability to generate or recall Harry Potter-related content.'' This claim is shown to be overbroad. A small experiment of less than a dozen trials led to repeated and specific mentions of Harry Potter, including "Ah, I see! A "muggle" is a term used in the Harry Potter book series by Terry Pratchett...''

The voluminous nature of geospatial temporal data from physical monitors and simulation models poses challenges to efficient data access, often resulting in cumbersome temporal selection experiences in web-based data portals. Thus, selecting a subset of time steps for prioritized visualization and pre-loading is highly desirable. Addressing this issue, this paper establishes a multifaceted definition of salient time steps via extensive need-finding studies with domain experts to understand their workflows. Building on this, we propose a novel approach that leverages autoencoders and dynamic programming to facilitate user-driven temporal selections. Structural features, statistical variations, and distance penalties are incorporated to make more flexible selections. User-specified priorities, spatial regions, and aggregations are used to combine different perspectives. We design and implement a web-based interface to enable efficient and context-aware selection of time steps and evaluate its efficacy and usability through case studies, quantitative evaluations, and expert interviews.

Reframing a negative into a positive thought is at the crux of several cognitive approaches to mental health and psychotherapy that could be made more accessible by large language model-based solutions. Such reframing is typically non-trivial and requires multiple rationalization steps to uncover the underlying issue of a negative thought and transform it to be more positive. However, this rationalization process is currently neglected by both datasets and models which reframe thoughts in one step. In this work, we address this gap by augmenting open-source datasets for positive text rewriting with synthetically-generated Socratic rationales using a novel framework called \textsc{SocraticReframe}. \textsc{SocraticReframe} uses a sequence of question-answer pairs to rationalize the thought rewriting process. We show that such Socratic rationales significantly improve positive text rewriting for different open-source LLMs according to both automatic and human evaluations guided by criteria from psychotherapy research.

Why scam obituaries are edging out earnest ones, with the help of artificial intelligence and an adept Google game. Subscribe to Slate Plus to access ad-free listening to the whole What Next family and across all your favorite Slate podcasts. Subscribe today on Apple Podcasts by clicking "Try Free" at the top of our show page. Sign up now at slate.com/whatnextplus to get access wherever you listen.

Music-based reminiscence has the potential to positively impact the psychological well-being of older adults. However, the aging process and physiological changes, such as memory decline and limited verbal communication, may impede the ability of older adults to recall their memories and life experiences. Given the advanced capabilities of generative artificial intelligence (AI) systems, such as generated conversations and images, and their potential to facilitate the reminiscing process, this study aims to explore the design of generative AI to support music-based reminiscence in older adults. This study follows a user-centered design approach incorporating various stages, including detailed interviews with two social workers and two design workshops (involving ten older adults). Our work contributes to an in-depth understanding of older adults' attitudes toward utilizing generative AI for supporting music-based reminiscence and identifies concrete design considerations for the future design of generative AI to enhance the reminiscence experience of older adults.

Maxwell Tani is known for his work on an obituary beat of sorts. A media reporter at Semafor, he always seems to be the first person to break news whenever something terrible happens for journalists at one outlet or another. He's been busy: According to one tabulation, more than 500 journalists were laid off just in January. A scroll through Tani's account on X surfaces a glut of executive memos, couched in corporate-speak, informing staff that they'll soon be laid off--at Business Insider, Engadget, the Messenger, Vice, and the Wall Street Journal. Sometimes he shares the news of an impending layoff before these memos even go out--and before employees have been informed. Slate spoke with Tani about what it's like to document the worst moments on the media beat, and how he feels about his place in the news-about-the-news ecosystem. We also tried to diagnose the ills of the industry--and find bright spots ahead.

Milind Tambe is the winner of the 2024 AAAI Award for Artificial Intelligence for the Benefit of Humanity. This award recognizes positive impacts of artificial intelligence to protect, enhance, and improve human life in meaningful ways. Milind gave an invited talk at the AAAI Conference on Artificial Intelligence, in which he spoke about some of the work that won him the award. For more than 15 years, Milind and his team have been focused on advancing AI and multi-agent systems for three purposes: public health, conservation, and public safety and security. The emphasis in all cases has been to optimise limited intervention resources.

Generative AI has the potential to create a new form of interactive media: AI-bridged creative language arts (CLA), which bridge the author and audience by personalizing the author's vision to the audience's context and taste at scale. However, it is unclear what the authors' values and attitudes would be regarding AI-bridged CLA. To identify these values and attitudes, we conducted an interview study with 18 authors across eight genres (e.g., poetry, comics) by presenting speculative but realistic AI-bridged CLA scenarios. We identified three benefits derived from the dynamics between author, artifact, and audience: those that 1) authors get from the process, 2) audiences get from the artifact, and 3) authors get from the audience. We found how AI-bridged CLA would either promote or reduce these benefits, along with authors' concerns. We hope our investigation hints at how AI can provide intriguing experiences to CLA audiences while promoting authors' values.