electronics-logo

Journal Browser

Journal Browser

AI-Driven Frameworks for Human–Computer Interaction

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 15 January 2027 | Viewed by 3072

Editor


E-Mail Website
Guest Editor

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) is reshaping the future of human–computer interactions (HCIs) by enabling systems that understand, learn from and adapt to human behavior. As AI becomes increasingly embedded in our daily lives, new frameworks are emerging that combine intelligent computation with user-centered design principles to create more natural, responsive and personalized interaction experiences. The integration of AI-driven models into HCIs has the potential to revolutionize communication, accessibility, education and creative expression.

The Special Issue “AI-Driven Frameworks for Human-Computer Interaction” in Electronics explores the frontier where AI meets HCIs. We aim to gather innovative contributions that investigate algorithms, architectures, frameworks and experimental methods enhancing human–AI collaboration. This Special Issue welcomes studies that address both theoretical and practical aspects of intelligent interaction systems, emphasizing explainability, trust and ethical design.

General Description

The objective of this Special Issue is to advance the understanding of how AI technologies can be leveraged to create intelligent, adaptive and context-aware interaction systems that improve human experience. Submissions may include original research articles, surveys or application studies presenting novel methodologies, frameworks and tools that bridge AI techniques and HCI principles. We encourage interdisciplinary perspectives combining artificial intelligence, cognitive science, data analytics and educational research.

Potential Topics

Topics of interest include, but are not limited to:

  • Machine learning and deep learning for adaptive and intelligent interfaces
  • Multimodal interaction (visual-, auditory-, haptic-, gesture- or speech-based systems)
  • Affective computing and emotion-aware systems
  • Conversational AI and intelligent virtual assistants
  • Human–robot interactions and embodied AI frameworks
  • Cognitive modeling and user intent prediction
  • Trust, transparency and ethics in AI-driven HCI
  • Real-time perception and decision-making in interactive environments
  • Generative AI for interface and interaction design
  • Creation of prompt engineering techniques within AI-driven systems
  • Frameworks that integrate prompt engineering into educational processes
  • Prompt Engineering as a Reflective Pedagogical Practice
  • AI and Prompt Engineering in Education
  • AI-based assistive and accessibility technologies
  • Evaluation methods for intelligent and adaptive user interfaces

By combining insights from AI, HCIs and education, this Special Issue aims to foster discussion and innovation toward next-generation systems that are not only intelligent but also meaningful, inclusive and human-centered.

We look forward to your valuable contributions to this Special Issue.

Dr. George Kokkonis
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • AI
  • HCI
  • intelligent virtual assistants
  • prompt engineering
  • AI-driven HCI
  • human–robot interactions

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

27 pages, 483 KB  
Article
A Conversational Agent with Hybrid NLU and Dual-Corpus RAG for KPI Alert Management in Tourism Business Intelligence
by Alberto Jiménez-Sánchez, Clara Rodríguez-Marcos, Silvia Domínguez-Castro, Albano Carrera and Ricardo S. Alonso
Electronics 2026, 15(16), 3704; https://doi.org/10.3390/electronics15163704 - 19 Aug 2026
Abstract
Monitoring operational Key Performance Indicators (KPIs) in Business-to-Business (B2B) tourism platforms demands continuous reconfiguration of alert systems, a task that conventional interfaces render inaccessible to non-technical stakeholders confronted with multi-screen forms and proprietary identifiers. This paper presents a conversational agent that lets such [...] Read more.
Monitoring operational Key Performance Indicators (KPIs) in Business-to-Business (B2B) tourism platforms demands continuous reconfiguration of alert systems, a task that conventional interfaces render inaccessible to non-technical stakeholders confronted with multi-screen forms and proprietary identifiers. This paper presents a conversational agent that lets such users create, modify, list, and explain KPI alerts through natural language, while guaranteeing the structural correctness of every configuration. Its core contribution is a schema-derived slot-completeness model of nine slot groups constraining a Large Language Model (LLM) tool-calling agent, paired with normalisation patterns derived at runtime from live database metadata and a bounded validation loop returning field-level errors to the model. A dual-corpus Retrieval-Augmented Generation module grounds the agent’s knowledge branch in schema documentation and a JSON-LD ontology, while configuration is grounded in live metadata; a human-in-the-loop checkpoint precedes every commit. The system is deployed as a prototype and evaluated in an automated pilot over a 50-utterance corpus, where it reaches 81.2% exact configuration match against 38.5% for the strongest unconstrained baseline (+42.7 percentage points, McNemar p<0.001) and emits no invalid schema identifier, against 15.8% for that baseline. A single-layer ablation locates the effect in the schema-aware tool layer. Corpus, annotations, prompts and evaluation scripts are released for replication. Full article
(This article belongs to the Special Issue AI-Driven Frameworks for Human–Computer Interaction)
Show Figures

Figure 1

38 pages, 2375 KB  
Article
A Novel Dual-Loop Causality-Traceable Retrieval Framework for Long-Horizon Conversational Agents
by Din-Yuen Chan, Chih-Yu Cheng, Jhing-Fa Wang and Shih-Pang Tseng
Electronics 2026, 15(11), 2373; https://doi.org/10.3390/electronics15112373 - 1 Jun 2026
Viewed by 566
Abstract
In long-horizon multi-party conversations, human-centric AI agents face a persistent structural problem: similarity-based retrieval may fail to reconnect semantically dispersed fragments of the same evolving event. This problem severely weakens causal continuity and multi-hop context recovery. To improve attribution trust and reduce structural [...] Read more.
In long-horizon multi-party conversations, human-centric AI agents face a persistent structural problem: similarity-based retrieval may fail to reconnect semantically dispersed fragments of the same evolving event. This problem severely weakens causal continuity and multi-hop context recovery. To improve attribution trust and reduce structural erasure, we propose MemLoom, a dual-loop causality-traceable retrieval framework that organizes conversational history as an event memory graph. MemLoom decouples latency-sensitive online interaction from off-peak structural curation through online event formation, sentence-level buffering, asynchronous neuro-symbolic graph synthesis, and bounded dual-stream retrieval. Evaluations across QMSum, LoCoMo, and the synthetic causal diagnostic suite (SCDS) support the structural utility of MemLoom. For LoCoMo, under our unified local evaluation setup, MemLoom shows favorable temporal and multi-hop reasoning results (J = 65.77 and 58.14) relative to contemporary agentic baselines, such as Mem0, Zep, and A-Mem. For SCDS, within a controlled diagnostic setting, it recovers demanded causal chains more reliably than GraphRAG (SCR = 0.72 vs. 0.35) and maintains stronger answer-level auditability (AA = 0.80 vs. 0.50). This is achieved with a bounded online P95 latency of 1.67 s. These results indicate that asynchronous dual-loop stewardship has practical value for causality-traceable, event-centric conversational memory in multi-party settings. Full article
(This article belongs to the Special Issue AI-Driven Frameworks for Human–Computer Interaction)
Show Figures

Figure 1

33 pages, 2088 KB  
Article
Reconceptualizing Prompt Engineering as Reflective Professional Practice: A Framework for Teacher Development
by Ioannis Dourvas, George Kokkonis and Sotirios Kontogiannis
Electronics 2026, 15(5), 930; https://doi.org/10.3390/electronics15050930 - 25 Feb 2026
Cited by 2 | Viewed by 1923
Abstract
The rapid integration of generative AI in education often frames teachers as technology users who primarily need technical training. Existing prompt engineering frameworks offer technical guidance but have limited grounding in theories of teacher professional development or reflective practice. This misses a key [...] Read more.
The rapid integration of generative AI in education often frames teachers as technology users who primarily need technical training. Existing prompt engineering frameworks offer technical guidance but have limited grounding in theories of teacher professional development or reflective practice. This misses a key feature of prompt engineering: prompting can externalize pedagogical thinking, making AI interaction a process of knowledge externalization. Through systematic conceptual analysis, this paper proposes a reconceptualization of prompt engineering from a technical competency to a reflective professional practice. The methodology integrates three theoretical traditions: Schön’s reflective practice theory (for externalizing tacit knowledge), Wiggins and McTighe’s backward design (for structuring instructional decisions), and Celik’s AI-TPACK framework (as integrated knowledge base). This synthesis suggests that effective prompting can be understood as an act of pedagogical externalization requiring integrated professional knowledge. The paper develops a seven-strategy framework (RPE framework) as an analytic lens for examining prompt engineering sophistication. This theoretical framework offers theory-derived hypotheses that require future empirical validation rather than presenting verified outcomes. Ultimately, the RPE framework offers a conceptual basis for potentially shifting the focus from technical training to teacher professional development by repositioning educators as AI-assisted instructional designers rather than mere AI users. Full article
(This article belongs to the Special Issue AI-Driven Frameworks for Human–Computer Interaction)
Show Figures

Figure 1

Back to TopTop