Sam Passmore, Lila San Roque, Kirsty Gillespie, Saurabh Nath, Kira Davey, Keira Mullan, Tim Cawley, Jennifer Biggs, Rosey Billington, Bethwyn Evans, Nick Thieberger, Danielle Barth. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This study introduces a novel Haptic Virtual Reality (HVR) simulator for intravenous (IV) needle insertion training, aiming to enhance traditional methods like manikins. Developed using a Meta Quest 2 headset, it incorporates two haptic devices: a haptic glove (SenseGlove Nova) for stabilization and a haptic stylus (Geomagic Touch) for needle insertion simulation, all integrated within Unity. A second prototype using a VR touch controller was created for user performance comparison. Both prototypes provide immersive experiences for hand-eye coordination and psychomotor skills. An evaluation experiment with 23 nursing students compared the systems to a previously developed Haptic Mixed Reality (HMR) version. Over three weeks, with three 10-minute training sessions, improvements in success rates and confidence were observed. The study included a Task Load Index assessment, indicating a manageable workload. Results suggest the HVR IV needle insertion simulator's potential to enhance nursing education.

Sentiment analysis and opinion mining of the opinion-bearing text are important tasks in NLP.The Appraisal framework in systemic functional linguistics is a theory for analysing the linguistic patterns for expressing emotion and opinion.Manual annotation of appraisals however, requires linguistic expertise, and is costly and time-consuming.In this paper, we study how to automatically identify and tag appraisal text segments.We formulate the problem as a sequence tagging problem and propose a novel approach, Adaptive Appraisal (A 2 ), which employs task and sentiment adapters on pre-trained language models for sequence appraisal tagging.Experiments on user comments, blogs and microblogs show that A 2 outperforms baseline models and achieves good performance for cross-domain and crosslingual settings.Source code for A 2 is available at: https://github.com/ltian678/AA-code.git