Improving Conversations: Lessons Learnt from Manual Analysis of Chatbot Dialogues
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Evaluation in chatbot research is conducted through instruments for users' self reports of user experience, user observation and interviews, analyses of chatbot interaction, and physiological measurements.
“Evaluation in chatbot research is conducted by instruments for users' self reports of user experience [63], through user observation and interviews [75] and analyses of chatbot interaction [66], and also by physiological measurements [22].”
From Future directions for chatbot research: An interdisciplinary research agenda (2021) · cites this paper as [66]
The citation lists haven’t been fetched yet
References 10 · Cited by 51
- Authors
- Kvale, K., Sell, O. A., Hodnebrog, S., & Følstad, A.
- Affiliations
- Telenor (Norway) (NO)
- SINTEF (NO)
- Corresponding author
- Kvale, Knut
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2020
- Pages
- 187-200
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W3000303345
- Cited by
- 51
- References
- 10
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 6 · 2023: 14 · 2022: 8 · 2021: 15 · 2020: 1
- FWCI
- 3.62
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Organizational Behavior and Human Resource Management › Customer Service Quality and Loyalty
- Keywords
- chatbots, chatbot training, dialogue analysis, customer service, dialogue quality
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
