MétaCan
Menu
Back to cohort

Variability-Aware Architecture for Human-Chatbot Interactions: Taming Levels of Automation

2023· article· en· W4389576359 on OpenAlexaff
Glaucia Melo, Nathalia Nascimento, Paulo Alencar, Donald Cowan

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicContext-Aware Activity Recognition Systems
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsChatbotComputer scienceHuman–computer interactionContext (archaeology)AutomationArchitectureFocus (optics)Service (business)Software engineeringWorld Wide WebEngineering

Abstract

fetched live from OpenAlex

Human-chatbot interactions have become increasingly complex and dynamic. These interactions depend on a multitude of context-aware factors, including those related to the people involved, the environment, the tasks to be accomplished, and the system quality attributes. A key challenge is how to capture the context-aware factors in human-chatbot interactions that influence the levels of automation in autonomous systems. Another challenge is how to incorporate these factors in the architectural design of these systems to create personalized and contextually appropriate responses. This paper proposes a variability-aware feature-oriented architectural design for enhancing human-chatbot interactions. The architecture is designed to accommodate the dynamic and varying requirements of autonomous computing systems, with a particular focus on chatbots. The paper presents the steps involved in the architectural design and demonstrates its instantiation through a specific scenario involving customer service for financial services chatbots.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.006
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.003
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.006
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0000.000
Science and technology studies0.0010.002
Scholarly communication0.0030.002
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0010.000

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 head0.074
GPT teacher head0.337
Teacher spread0.263 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicContext-Aware Activity Recognition SystemsFrench-language works237,207