Can Machines Talk? : Comparison of Eliza with Modern Dialogue Systems
- Submitting institution
-
Coventry University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 11581450
- Type
- D - Journal article
- DOI
-
10.1016/j.chb.2016.01.004
- Title of journal
- Computers in Human Behavior
- Article number
- -
- First page
- 278
- Volume
- 58
- Issue
- -
- ISSN
- 0747-5632
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper reports on an experiment where 116 volunteers score the conversational ability of five modern chatbots and the classic 1960s chatbot Eliza. The study found a vast improvement in conversational ability since Eliza but also some demographic differences: women consistently scored systems higher than men, and those aged <25 scored systems higher than those age 25+. Published in a top-ranked HCI journal, this paper has received 100+ citations to date (GoogleScholar). Personal interaction and improvement in usability are driving the growth in conversational agents; but this paper suggested that a renewed focus on diversity of evaluation data is required.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
