MétaCan
Menu
Back to cohort
Record W4411121473 · doi:10.1108/mip-07-2024-0525

Insights from customers’ chats with bots and human agents

2025· article· en· W4411121473 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueMarketing Intelligence & Planning · 2025
Typearticle
Languageen
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsMcGill University
Fundersnot available
KeywordsBusinessAdvertisingMarketingComputer scienceInternet privacy

Abstract

fetched live from OpenAlex

Purpose The research aims to provide companies knowledge of (1) why customers use the chat feature, (2) who – the agent or the bot – is more similar (in content) to the customer and (3) whether and how this similarity impacts the customer’s engagement during the chat. Design/methodology/approach I conducted three analyses, each of which uses machine learning. Findings Analysis 1 reveals that customers prefer chatting with an agent (vs. the bot) when they seek detailed or sensitive information. Analysis 2 demonstrates that relative to the bot, the agent is more similar (in content) to the customer. Analysis 3 uses guided latent Dirichlet allocation and gradient boosting (XGBoost) to show that matching the customer on the dominant topic boosts customer engagement during the chat. Research limitations/implications The findings help academics know why customers choose an agent versus a bot and whether this choice helps or hurts their engagement. Practical implications The findings help retail managers design better chat features and chatbots, thus improving customer engagement. Originality/value I am aware of no research in marketing or business that has provided evidence on customers’ choice of agent versus bot and the engagement consequences of this choice.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.234
Threshold uncertainty score0.812

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.022
GPT teacher head0.300
Teacher spread0.278 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it