Travel safety for women is a concern, particularly in India, where gender-based violence and harassment are significant issues. This study examines how the perception of safety influences women’s travel behaviour and assesses the potential of technology solutions to ensure their safety. Additionally, it explores how AI and machine learning techniques may be leveraged to enhance women’s travel safety. A comprehensive mobility survey was designed to uncover the complex relationship between travel behaviour, reasons for mode choice, built environment, feelings, future mobility, and technological solutions. The responses revealed that security and safety are the most critical factors affecting women’s travel mode choices, with 54% and 41%, respectively. Moreover, over 80% of women indicated a willingness to change their travel behaviour after experiencing fear, anxiety, or danger during their everyday journeys. Participants were 24% less willing to use ride-sharing services than ride-hailing services, which could affect the transition towards more sustainable transportation options. Furthermore, AI-based sentiment analysis revealed that 46% of the respondents exhibited signs of ‘anger’ regarding what could help women feel safer in transient environments. The practical implications of this study’s findings are discussed, highlighting the potential of AI to enhance travel safety and optimise future sustainable transport planning.

Book search is a challenging task due to discrepancies between the content and description of books, on one side, and the ways in which people query for books, on the other. However, online reviewers provide an opinionated description of the book, with alternative features that describe the emotional and experiential aspects of the book. Therefore, locating emotional sentences within reviews, could provide a rich alternative source of evidence to help improve book recommendations. Specifically, sentiment analysis (SA) could be employed to identify salient emotional terms, which could then be used for query expansion? This paper explores the employment ofSA based query expansion, in the book search domain. We introduce a sentiment-oriented method for the selection of sentences from the reviews of top rated book. From these sentences, we extract the terms to be employed in the query formulation. The sentence selection process is based on a semi-supervised SA method, which makes use of adapted word embeddings and lexicon seed-words.Using the CLEF 2016 Social Book Search (SBS) Suggestion TrackCollection, an exploratory comparison between standard pseudo-relevance feedback and the proposed sentiment-based approach is performed. The experiments show that the proposed approach obtains 24%-57% improvement over the baselines, whilst the classic technique actually degrades the performance by 14%-51%.

As the global population of older adults grows, AI-powered Voice Assistants (VAs) are explored as tools to mitigate loneliness, social isolation, and cognitive decline. By enabling intuitive, hands-free interaction, VAs provide a means to enhance independence, emotional well-being, and daily functioning for older adults. This paper presents a systematic review on older adults’ interactions with VAs, analysing 48 studies, which is more than double the scope of prior reviews. Studies were selected from an initial pool of 109 publications across three major Human-Computer Interaction (HCI) databases: Scopus, PubMed, and the ACM Digital Library. Through thematic analysis of research questions addressed in the selected studies, six key research themes were identified: (1) usage patterns and interaction behaviours, (2) adoption barriers and learnability challenges, (3) user experience and satisfaction, (4) cognitive and emotional impacts, (5) design considerations for older adults, and (6) future directions. A major finding is the VAs potential role in offering emotional companionship, particularly for socially isolated individuals. However, findings also suggested that technological illiteracy, trust concerns, and usability challenges hinder VAs’ adoption. This review highlights several important gaps in the existing literature. There is a lack of longitudinal research, and limited understanding of how these systems are used in real-world settings compared to controlled environments. Many studies also fail to report participants’ levels of technological experience and rely on samples that are not fully representative of the broader older adult population. Taken together, these limitations suggest that current research may not fully capture long-term use, contextual variability, or the diversity of older adults. In response, this paper outlines a set of evidence-based recommendations for future research and design. It emphasises the need to account for novelty effects in short-term studies and to adopt more ecologically valid approaches, such as in-home or longer-term deployments. It also highlights the importance of minimising artificial constraints that may influence user behaviour, and of systematically documenting user–device interactions alongside participants’ digital literacy. These steps can support more rigorous and representative evaluation practices, contributing to the development of voice assistant technologies that are better aligned with real-world use and more accessible, ethical, and effective for older adults.