Science AI Journal
Computer Science · Research topic

Open research questions in Expert finding and Q&A systems

69 gap statements mined from Expert finding and Q&A systems papers in our 4.5M-paper local library, which holds 469 papers on the topic — drawn mostly from each paper's own stated research gap, future-work, challenge and limitation notes, and its abstract. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one.

Choosing where to publish on Expert finding and Q&A systems? See the ranked Computer Science journals.

What the literature leaves open

  • The study remains limited in the extent to which it can evaluate content-level source characteristics. The local source orientation measure may undercount locally relevant sources that operate under generic top-level domains. The study does not examine the internal model architectures, retrieval pipelines, or training corpora of the underlying LLM systems.

    Human-Centric Auditing of AI-Powered Generative Search: When Citations Diverge from Rankings · 2026 · DOI

  • Practice and policy abstract Generative artificial intelligence (AI) is reshaping online knowledge-sharing, but its effects on voluntary user contributions remain uncertain.

    Examining the Impact of Generative AI on Users’ Voluntary Knowledge Contribution: Evidence from a Natural Experiment on Stack Overflow · 2025 · DOI

  • Traditional study methods have limitations. There is a need for a 'smarter study' environment that can support academic research, teaching preparation, and student learning.

    Smarter Study with Notebook: Transforming Academic Research and Teaching · 2026 · DOI

  • MeetInsight is an AI-based system designed to make meetings more useful, organized, and easy to understand. It helps users record meetings, convert speech into text, information by asking and quickly find questions. This reduces the need for manual note-taking and saves a lot of time.

    Meetinsight: AI-Powered Meeting Intelligence · 2026 · DOI

  • The impact of financial incentives on answer quality is complex and multifaceted. Online health Q&A communities face the issue of under-provision, where users lack motivation to contribute content.

    Same coin, different sides: an examination of the influence of financial incentives on online health-related answer quality from a linguistic features perspective · 2026 · DOI

  • The lack of effective audience models that can distinguish between what users know and what they misunderstand.

    Contextualized Dynamic Explanations: A Vision · 2026

  • B. Limitations Despite promising results, the current framework has certain limitations. First, the system performance depends heavily on the quality of input resumes. Poorly formatted PDFs or image-based resumes may reduce Textract OCR accuracy. Second, the BERT NER model was trained primarily on IT domain resumes, potentially affecting accuracy for other sectors like healthcare or legal.

    Ai Powered Ats Resume Screeing And Job Recommendation System · 2026 · DOI

  • While blind or low-vision (BLV) scientists have traditionally relied on static alternative text to access figures in papers, the rise of artificial intelligence (AI) has made interactive question-answering (QA) a feasible paradigm for visual exploration; yet little is known about how scientists use visual QA in practice or how to improve its accessibility.

    Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists · 2026

  • Although prior work has explored AI support for isolated interviewing tasks, such as script generation and follow-up question generation, little is known about how integrated support affects the interview and what requirements artifacts emerge.

    AI-assisted Script Management for Requirements Elicitation Interviews · 2026

  • Future work should explore discourse-aware architectures that better capture implicit criticism and hedging strategies common in academic writing.

    From reviews to decisions: A joint multitask aspect sentiment leveraged framework for assisting decision prediction from academic peer reviews · 2026 · DOI

  • Another challenge is the need to develop custom-developed web crawlers to collect data not included in the dump file.

    Direct and moderating effects of generative AI on new user retention in social Q&A platforms: evidence from Stack Overflow · 2026 · DOI

  • Previous knowledge selection methods have shortcomings, such as relying too heavily on dialogue contexts or over-emphasizing new information. The challenge of maintaining well-balanced coherence and knowledge diversity in knowledge-grounded conversations is not addressed by previous methods.

    CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations · 2023 · DOI

  • The topic of social aspects of educational communication and technology is difficult to define. There is a need for new research approaches beyond the current methods.

    Comment: A source of questions · 1985 · DOI

  • Converting texts into a form more amenable to processing is a goal of computational linguistics. Rules are needed to determine the relationship between sentences and to disambiguate sentences based on prior context.

    Natural language processing · 1984 · DOI

  • The study had a limited sample size of 96 individuals in 48 dyads. The instructions did not indicate how long the conversations would last. The study did not investigate how the participants were to achieve their conversational goals.

    To Ask or Not to Ask: Is That a Question? · 1983 · DOI

  • One The MeetInsight system can be further enhanced by adding several advanced features to improve its usability important improvement is real-time transcription, which will allow users to see the meeting text instantly as the conversation happens. Another useful feature is automatic meeting summarization, where the system can generate key points, decisions, and action items from the discussion.

    Meetinsight: AI-Powered Meeting Intelligence · 2026 · DOI

  • Creating effective audience models that can distinguish between what users know and what they misunderstand.

    Contextualized Dynamic Explanations: A Vision · 2026

  • One important enhancement is the integration of image input capability. Another useful extension is the support for file uploads. The implementation of text-to-speech functionality can significantly improve user experience.

    Auto Generated Domain Specific Chat Bot using AI Agent · 2026 · DOI

  • Manual preparation of question papers can result in repeated questions, uneven distribution across modules, and formatting errors. Existing examination systems generally require manual question selection.

    Question Paper Generator · 2026 · DOI

  • Needless to say, the overall framework provided in this work is not limited to the specific user facility, and can be easily applied to other facilities at ORNL, other national laboratories, and even major funding agencies like DOE, NSF and NIH.

    LLMs can assist with proposal selection at large user facilities · 2026 · DOI

  • Although previous studies have examined the effects of knowledge content, knowledge source credibility and the personal characteristics of knowledge seekers on knowledge adoption in virtual Q&A communities from a static perspective, the impact of answer deviation on knowledge adoption has rarely been explored from a context-based perspective.

    Two-way deviation: the impact of the deviation of horizontal and vertical answers on knowledge adoption in virtual Q&A communities · 2024 · DOI

  • This paper is intended for reflective information professionals who seek a greater understanding of the issues related to adopting conversational agents in libraries, as this topic is scarcely covered in the LIS literature.

    Artificially intelligent conversational agents in libraries · 2010 · DOI

  • Advances in natural language processing may bring database retrieval and text structuring tasks closer together. Natural language processing may make it more efficient and effective to record some types of information through a man-machine conversation.

    Natural language processing · 1984 · DOI

  • Further research on the governance of algorithmic visibility and citation fairness in AI systems, - Examining how source visibility is configured in AI-mediated…

    Human-Centric Auditing of AI-Powered Generative Search: When Citations Diverge from Rankings · 2026 · DOI

  • Investigating the impact of generative AI on other social Q&A platforms, - Examining the effects of generative AI on user retention in different…

    Direct and moderating effects of generative AI on new user retention in social Q&A platforms: evidence from Stack Overflow · 2026 · DOI

Most-cited papers in Expert finding and Q&A systems

Most recent work

Find a gap in your own Expert finding and Q&A systems sub-topic

This page shows what the Expert finding and Q&A systems literature already flags as unresolved. To narrow it to your specific question, search the Research Gap Finder: the search is free with a free account and lists the papers closest to your topic first. Unlocking that topic (50 credits, charged once) fills the comparison table from our 4.5M-paper local library and writes the gaps from its rows.

Open the Research Gap Finder →

Related topics in Computer Science

Online Learning and Analytics
1,068 open questions
AI in Service Interactions
888 open questions
Virtual Reality Applications and Impacts
796 open questions
Computational Drug Discovery Methods
691 open questions
Quantum Computing Algorithms and Architecture
688 open questions
Teaching and Learning Programming
663 open questions
Digital literacy in education
591 open questions
Topic Modeling
565 open questions
Open questions raised by papers listed on this page include: (1) The study remains limited in the extent to which it can evaluate content-level source characteristics (“Human-Centric Auditing of AI-Powered Generative Search: When Citations Diverge…”, 2026); (2) There is a need for a 'smarter study' environment that can support academic research, teaching preparation, and student learning (“Smarter Study with Notebook: Transforming Academic Research and Teaching”, 2026); (3) Future work should explore discourse-aware architectures that better capture implicit criticism and hedging strategies common in academic writing (“From reviews to decisions: A joint multitask aspect sentiment leveraged…”, 2026); (4) The lack of effective audience models that can distinguish between what users know and what they misunderstand (“Contextualized Dynamic Explanations: A Vision”, 2026); (5) There is a need for new research approaches beyond the current methods (“Comment: A source of questions”, 1985). 69 gap statements have been mined from Expert finding and Q&A systems papers in our 4.5M-paper local library, which holds 469 papers on the topic; the gaps come from whichever of those papers state one. They are mostly the research gaps the authors state and the papers' abstracts, plus future-work, limitations and challenges passages. The ones listed below are a selection still marked open; each names the study that raised it, with a DOI link where the paper has one, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 120,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? Acceptance odds for top, mid and open/emerging journals, in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck for prior publication across 7 sources and our local library.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

How Pre-Check worksHow AI Review works

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.