Interaction Design & Architectures最新文献_第2页

Aspect-Based Adversarial Attack Against Opinion Analysis Models with an Educational Perspective 教育视角下基于方面的对意见分析模型的对抗性攻击

Interaction Design & Architectures Pub Date : 2026-08-31 DOI: 10.55612/s-5002-069-014

Monserrat Vázquez-Hernández,Luis Alberto Morales-Rosales,Ignacio Algredo-Badillo,Luis Villaseñor-Pineda

{"title":"Aspect-Based Adversarial Attack Against Opinion Analysis Models with an Educational Perspective","authors":"Monserrat Vázquez-Hernández,Luis Alberto Morales-Rosales,Ignacio Algredo-Badillo,Luis Villaseñor-Pineda","doi":"10.55612/s-5002-069-014","DOIUrl":"https://doi.org/10.55612/s-5002-069-014","url":null,"abstract":"Analyzing students’ opinions about classes, instructors, and the overall learning environment enables institutions to understand students’ needs and propose improvements to enhance the learning process. Furthermore, analyzing opinions at aspect-level allows a detailed analysis and helps to identify the relevant aspects that require attention to enrich the students’ experience. Currently, opinion analysis systems implement deep learning models to increase precision. However, these models can be misled by strategically modified inputs, known as adversarial examples, producing incorrect classifications. In this work, we analyze adversarial examples and their behavior in aspect-level sentiment analysis models to design aspect-aware modifications. Specifically, we define a model for generating aspect-level adversarial examples that modify inputs by targeting aspect–term relationships. The proposed model reduces accuracy by 20.90%, highlighting vulnerabilities in aspect-level models, where even small and targeted changes can degrade performance, providing a foundation for the development of defense mechanisms to ensure reliable predictions.","PeriodicalId":524244,"journal":{"name":"Interaction Design & Architectures","volume":"185 1","pages":"310-334"},"PeriodicalIF":0.0,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149151694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Embodied Multimodal Dialogue in Interactive Art Installations: Toward Sustainable Creative Practices 互动艺术装置中的多模式对话：走向可持续的创作实践

Interaction Design & Architectures Pub Date : 2026-08-31 DOI: 10.55612/s-5002-069-004

Arminda Guerra

{"title":"Embodied Multimodal Dialogue in Interactive Art Installations: Toward Sustainable Creative Practices","authors":"Arminda Guerra","doi":"10.55612/s-5002-069-004","DOIUrl":"https://doi.org/10.55612/s-5002-069-004","url":null,"abstract":"Multimodal interaction has become a central concern in contemporary Human–Computer Interaction (HCI), particularly in contexts where bodily engagement and sensory integration are fundamental to user experience. Interactive art installations constitute a specific domain within HCI in which interaction is exploratory, situated, and often resistant to conventional usability evaluation. Although principles from User-Centered Design (UCD), Interaction Design, and User Experience (UX) are frequently invoked to describe such systems, their empirical application to interactive art remains methodologically underspecified. This paper examines multimodal dialogue as an analytical lens for understanding interaction in artistic installations. Three interactive installations, SandBox, TIDE (IDEArt), and Threshold, are analyzed as qualitative case studies using a unified research design. Data were collected through systematic observation, semi-structured interviews, and audiovisual documentation, and analyzed using thematic analysis. The results identify recurrent patterns of embodied interaction, sensory exploration, and interpretative meaning-making across the three installations. In preference to proposing a new theoretical framework or quantitative evaluation model, this study contributes a methodologically transparent approach to investigating multimodal dialogue in interactive art, demonstrating, through evidence gathered across three case studies, how embodied and interpretative forms of interaction support sustained engagement, methodological reuse, and the long-term relevance of interactive installations beyond technological novelty.","PeriodicalId":524244,"journal":{"name":"Interaction Design & Architectures","volume":"8 1","pages":"78-95"},"PeriodicalIF":0.0,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149151687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sustainability and Innovation in Creative Industries and Design. 创意产业与设计的可持续发展与创新。

Interaction Design & Architectures Pub Date : 2026-08-31 DOI: 10.55612/s-5002-069-001psi

Stefan Greuter,Tonya Meyrick,Fatma Al Aamri

引用次数: 0

Improving the experience and mobility of the Elderly at the Beach from a Product Design approach 从产品设计的角度改善老年人在海滩的体验和活动能力

Interaction Design & Architectures Pub Date : 2026-08-31 DOI: 10.55612/s-5002-069-010

Mariana Santos,Teresa Cotrim,Inês Veiga

引用次数: 0

Enhancing AI Dialogue through Dual Role Assignment: An Investigation of User-AI Professional Role Sharing 通过双重角色分配加强人工智能对话：用户-人工智能专业角色共享研究

Interaction Design & Architectures Pub Date : 2026-08-31 DOI: 10.55612/s-5002-069-011

Keisuke Sato

{"title":"Enhancing AI Dialogue through Dual Role Assignment: An Investigation of User-AI Professional Role Sharing","authors":"Keisuke Sato","doi":"10.55612/s-5002-069-011","DOIUrl":"https://doi.org/10.55612/s-5002-069-011","url":null,"abstract":"Conversational AI systems increasingly employ role/persona prompting to elicit domain-specific responses, yet roles are typically assigned only to the AI side while the user remains a neutral questioner. This study empirically investigates how dialogue content transforms when professional roles are assigned not only to the AI but also to the user, and when both parties share the same role. We conducted controlled dialogues about an identical line-drawing stimulus under four role-assignment conditions (no-role, AI-only role, user-only role, and both roles) across five professional roles (detective, psychologist, artist, architect, natural scientist) and four contemporary LLMs (ChatGPT-4o, OpenAI o1, Claude 3.5 Sonnet, Gemini 1.5 Pro), yielding 64 sessions and 320 question–response pairs. Quantitative term-frequency analysis of the detective role—presented as a representative case with the clearest lexical shifts—revealed that the shared-role condition increased domain-specific terminology compared to baseline and single-role conditions, a pattern also observed in the other four roles. Qualitative close readings of the detective role suggested that shared roles were associated with stronger expertise-oriented reasoning, multiperspectivity, and characteristics resembling professional peer exchange. Notably, user-side role assignment alone altered model responses even without an explicit AI role instruction. Cross-model comparisons under the shared detective-role condition showed that each LLM expressed the same role frame with distinct stylistic tendencies, supporting a two-layer interaction model in which externally imposed role frames set the discourse direction while model-specific traits shape expression style. These findings offer practical implications for prompt engineering, educational dialogue design, and expert-support systems. The full dataset is publicly available on Zenodo (DOI: 10.5281/zenodo.14567800).","PeriodicalId":524244,"journal":{"name":"Interaction Design & Architectures","volume":"1 1","pages":"233-257"},"PeriodicalIF":0.0,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149151696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0