AI evidence extraction

Designing Conversational Agents for Search String Development in Literature Reviews

Daniel Bierschwale, Phillip O. Gottschewski-Meyer, Thorsten Schoormann, Ralf Knackstedt · Journal of the Association for Information Systems · 2026

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

0/4

Quality (LMQS)

Evidence

Citations

0.00

FWCI

Methodology & findings

Study design

Design Science Research approach including interviews to understand the problem space, aggregation of design knowledge from multiple research streams, and instantiation of design features through systematic prompt engineering..

Primary method

Design science research

Main result

The study developed a conversational agent called STRINGI that "assists search string development through structured, guided, and pedagogically informed interactions." The research instantiated "22 design features through systematic prompt engineering" and contributes "a CA-based SLR support tool, a transparent design-features-to-prompt-transfer approach, and insights into the design of polyadic CA architectures."

Research paradigm

Design science research

Author conclusions

The authors conclude that STRINGI "offers potential for young researchers and students to both perform literature reviews as part of their work and develop their understanding of scientific principles and methods. The CA bridges methodological prescriptions and operational support, enabling deployment while advancing research practices and offering potential for education."

Risk of bias

No explicit discussion of bias mitigation strategies in abstract; Interview-based study design may be subject to selection bias in participant recruitment; Limited information on sample representativeness for the interview phase

Open questions raised

The abstract identifies that "search string development often lacks dedicated support" despite being essential for systematic literature reviews, and notes that "young researchers and interdisciplinary teams struggle with keyword identification, terminological heterogeneity, and database-specific syntax."
The paper identifies that "search string development often lacks dedicated support" despite numerous tools supporting downstream SLR phases. Young researchers and interdisciplinary teams struggle with keyword identification, terminological heterogeneity, and database-specific syntax.
The paper identifies that "search string development often lacks dedicated support" despite numerous tools supporting downstream SLR phases. The work addresses this gap through development of conversational agent-based support.

Data: not_statedCode: not_statedExtracted from: pdfAgreement 80%

Explore related topics

Systematic Review Automation Literature Discovery Design Science