phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | adaptive conversational agent design— “This research examines the influence of individualized CA design on the user experience.” | |
| claim-type | existence— “Initial results from our pilot study (n=37) confirm that individualized CA design can enhance the user experience.” | |
| method — evidence | — “To examine the influence of individualized CA design on the user experience and test our hypotheses, we conduct an online experiment applying a within-subject design (Erlebacher, 1977).” | |
| transfer | from communication science / social psychology (communication accommodation theory): the theory of how humans accommodate their speech to an interlocutor, re-applied to design a chatbot that accommodates its style to the user— “Our study will further contribute to research by adapting communication accommodation theory (Giles et al., 2010) to the context of human-AI interaction, thereby showing that adapting the CA’s communication style to users has the potential to positively influence their user experience.” | transfers[0] |
| mechanism | Accommodating one's communication style to the interlocutor signals an attitude toward them and thereby steers how the speaker and the interaction are evaluated— “The theory suggests that humans adapt their communication style to show their attitude toward the interlocutor and steer the evaluation of the speaker and the interaction (Giles et al., 2010).” | mechanisms[0] |
| mechanism | An interaction partner that accommodates the user's needs signals attention and caring, which raises perceived social presence, which in turn produces enjoyment— “When a (human or technology) interaction partner considers the needs and preferences of the interlocutor during the interaction, this signals attention and caring (Bitner et al., 1990; Giles et al., 2010), thereby enhancing the perceived social presence (Hess et al., 2009; Van Pinxteren et al., 2020).” | mechanisms[1] |
| mechanism | Matching the chatbot's communication style to the user's cognitive abilities lowers the cognitive effort the interaction demands and raises its efficiency, which drives re-use intention— “For example, if the CA’s communication style matches the user's cognitive abilities, this will likely decrease the required cognitive effort and improve interaction efficiency (Giles et al., 2010; Goodhue and Thompson, 1995).” | mechanisms[2] |
| mechanism | The unequal split between rational and intuitive participants left that group underpowered, producing the absence of significant differences— “A possible explanation could be the imbalance of the number of participants that were classified as rational or intuitive (10 compared to 4)—which will be addressed in the main study.” | mechanisms[3] |
| builds-on | communication accommodation theory (Giles et al., 2010)— “Drawing on communication accommodation theory (Giles et al., 2010), we derive a research model, that is tested in an online experiment.” | claim_relations[0] |
| extends | Altmeyer et al. (2020); Danckwerts et al. (2019); Gnewuch et al. (2020)— “However, the majority of prior studies on the individualization of CAs or AI-based systems has two crucial shortcomings: First, they do not explicitly adapt the system design to user characteristics (e.g., Altmeyer et al., 2020; Danckwerts et al., 2019; Gnewuch et al., 2020), yet only measure perceived individualization (i.e., instead of… | claim_relations[1] |
| sense | user experience - operationalised as three separate measured constructs: service satisfaction as the evaluative attribute, enjoyment as the hedonic one, re-use intention as the pragmatic one— “To evaluate the user experience, we draw on the overall evaluation of the interaction (i.e., service satisfaction), as well as hedonic (i.e., enjoyment) and pragmatic (i.e., re-use intention) attributes” | senses[0] |
| sense | satisfaction - a construct the paper notes is used for two different things across disciplines: user attitudes ABOUT A SYSTEM, or the perception of SERVICE INTERACTIONS— “Satisfaction is a central construct of interest in IS and other disciplines (e.g., marketing, service science) (Deng et al., 2010), used to measure user attitudes about a system (Melone, 1990) or the perception of service interactions (Oliver, 1980).” | senses[1] |
| control | attention check questions embedded in the instrument, with the seven data sets that failed them excluded before analysis — held — rules out inattentive responding - participants clicking through a questionnaire about conversational agents without reading it— “To ensure high-quality data, we excluded seven data sets due to inattention (i.e., when they failed attention check questions).” | controls[0] |
| edge | user experience —operationalised-as→ service satisfaction— “To evaluate the user experience, we draw on the overall evaluation of the interaction (i.e., service satisfaction), as well as hedonic (i.e., enjoyment) and pragmatic (i.e., re-use intention) attributes” | concept_edges[0] |
| outcome (stated by the tagger, no quotation) | control — held | controls[0] |
| for which use | limitation — everything reported: DESPITE ITS LIMITED SAMPLE SIZE, OUR PILOT STUDY OFFERS VALUABLE INSIGHTS - a pilot, treated as provisional pending the main study— “Despite its limited sample size, our pilot study offers valuable insights into the effect of individualized CAs on the user experience:” | limitations[0] |
| for which use | limitation — the user-experience responses specifically: IT IS WORTH CONSIDERING A BETWEEN-SUBJECTS DESIGN ... AS THIS PREVENTS PARTICIPANTS FROM BEING BIASED IN THEIR RESPONSES— “First, it is worth considering a between-subjects design instead of a within-subjects design, as this prevents participants from being biased in their responses to the user experience questionnaire by previous questions.” | limitations[1] |
| for which use | limitation — the null for cognitive style: A POSSIBLE EXPLANATION COULD BE THE IMBALANCE OF THE NUMBER OF PARTICIPANTS THAT WERE CLASSIFIED AS RATIONAL OR INTUITIVE (10 COMPARED TO 4)— “A possible explanation could be the imbalance of the number of participants that were classified as rational or intuitive (10 compared… | limitations[2] |
| for which use | limitation — the generality of the personalisation claim: only two user characteristics were studied, separately, so combinations remain untested | limitations[3] |
| for which use | limitation — the conclusion that individualised CA design improves user experience: the results report two exceptions in the rational/intuitive cognitive style group, one of them favouring the un-adapted agent on enjoyment | limitations[4] |
| for which use | limitation — these pilot ratings as unbiased measures of user experience: the authors state a within-subjects design was used and that a between-subjects design would prevent bias from previous questions Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[5] |
| for which use | limitation — generalising to adaptation on user characteristics in general: two were examined separately, and their combinations and other CA design characteristics were not Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[6] |
| for which use | limitation — these variables as directly observed: every construct is measured with item sets adopted from prior literature rather than developed or validated here Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[7] |
| replication | untested | |
| limitation | The pilot's sample was small and the authors treat the whole design as provisional pending a larger main study. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[0] |
| limitation | The within-subjects design may bias later user-experience responses; a between-subjects design is being considered instead. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[1] |
| limitation | The cognitive-style group was imbalanced (10 rational vs 4 intuitive), which may explain the absence of significant effects there. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[2] |
| limitation | Only two user characteristics were studied, and separately; other characteristics and their combinations remain unexamined. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[3] |
| limitation | The summarised benefit does not carry the exceptions the results report: in one group the adapted agent was no better on satisfaction, and the UN-adapted agent was rated higher on enjoyment. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
| limitation | The design used may bias the responses it collects, and the authors say a different design would prevent it. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[5] |
| limitation | Two user characteristics were examined, separately, and the authors state the interplay between them was not investigated. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[6] |
| limitation | The constructs are measured entirely by item sets borrowed from other studies, so the measurement inherits whatever those instruments assume. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[7] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | In the need-for-interaction group, both enjoyment and re-use intention were significantly higher for the chatbot adapted to the user than for the non-adapted chatbot. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[0] |
| finding | In the rational/intuitive cognitive-style group, none of the user-experience differences between the adapted and non-adapted chatbot reached statistical significance. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[1] |
| finding | The improvement in service satisfaction from individualization was not statistically significant. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[2] |
| finding | Individualization improved ratings in both groups except that, for cognitive-style adaptation, service satisfaction was unchanged and enjoyment was actually rated higher for the non-adapted chatbot. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[3] |
| finding | Enjoyment of the chatbot adapted to the user's need for interaction averaged 5.70 against 4.90 for the one-size-fits-all chatbot. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[4] |
| quantity | 37 — participants recruited for the pilot study Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[0] |
| quantity | 30 — usable data sets analysed after excluding inattentive participants Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[1] |
| quantity | seven — data sets dropped for failing attention checks Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[2] |
| quantity | 52 — participants in the pre-study used to set the classification thresholds Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[3] |
| quantity | 4.7 — threshold score on the 7-point scale above which a participant counts as having a high need for interaction Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[4] |
| quantity | mean = 5.70 compared to mean = 4.90 — enjoyment rating of the CA adapted to need for interaction versus the one-size-fits-all CA Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[5] |
| quantity | 90 — minimum sample size the power analysis requires for the planned main study Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[6] |
| quantity | n = 8 — participants in the two qualitative pre-tests validating the chatbots Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[7] |
| quantity | 10 compared to 4 — imbalance between participants classified as rational and as intuitive, offered as the reason for the null result in that group Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.quantities[8] |
| variable | user characteristic (moderator) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[1] |
| variable | user experience (dependent) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[2] |
| variable | experimental task (control) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.variables[4] |
| definition | conversational agents (CAs) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[0] |
| definition | cognitive style Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[1] |
| definition | intuitive cognitive style Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[2] |
| definition | rational cognitive style Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[3] |
| definition | need for interaction Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[4] |
| definition | user characteristics Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[5] |
| definition | enjoyment Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.definitions[6] |
| concept | conversational agents Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[0] |
| concept | user experience Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[1] |
| concept | service satisfaction Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[2] |
| t-test | as written: t-tests Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[0] |
| Wilcoxon signed-rank test V | as written: Wilcoxon signed rank tests Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[1] |
| p-value p | as written: p < .05 Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[2] |
| median split | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[3] |
| power analysis | as written: a priori power analysis using G*Power Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[4] |
| effect size (Cohen's d) d | as written: medium effect size (d = 0.5) Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[5] |
| standard deviation SD | as written: SD Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[6] |
When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824