MétaCan
Menu
Back to cohort
Record W4415226816 · doi:10.1016/j.geomat.2025.100079

Student chatbot use and perceptions in a course assignment: Comparing two geomatics courses

2025· article· en· W4415226816 on OpenAlexvenueno aff
Hartwig H. Hochmair

Bibliographic record

VenueGEOMATICA · 2025
Typearticle
Languageen
FieldComputer Science
TopicAI in Service Interactions
Canadian institutionsnot available
Fundersnot available
KeywordsChatbotGeomaticsGeospatial analysisPerceptionSet (abstract data type)ToxapheneData collection

Abstract

fetched live from OpenAlex

Recent advancements in generative AI have significantly impacted higher education, especially through the integration of AI chatbots in course design, teaching, administration, and student support. However, empirical research on chatbot use in Geomatics education remains limited, particularly regarding students’ choice of platforms, preferences for multimodal prompts, perceived quality of chatbot responses, challenges encountered, and follow-up strategies. To address this gap, we investigated how students used chatbots as part of a given discussion assignment in two university-level Geomatics courses offered in Spring 2025: Measurement Science (n = 20) and Geospatial Analysis (n = 25). As part of the discussion assignment students were tasked to design five prompts based on lecture content, submit them to one of seven chatbot platforms, rate the responses, and provide written justifications. Student interactions were analyzed using regression models that accounted for repeated prompts per student. These models examined how platform choice, prompt modality, and other prompt characteristics influence response ratings and follow-up behavior. Findings revealed distinct patterns. For example, students in Geospatial Analysis posed proportionally more conceptual than computational questions; follow-up prompts were more likely when chatbots produced computational errors than when explanations were unsatisfactory; and data-enhanced prompts (e.g., with tabular inputs) received lower ratings than textual ones, underscoring unmet expectations for chatbot-based GIS data processing. The study concludes with a set of best practice recommendations for chatbot use based on these two courses, which may inform Geomatics instruction in similar university-level courses. • Students rated chatbot responses more favorably for surveying-related prompts than for GIS-related prompts • Multimodal prompts encouraged greater curiosity and exploration among students • Computation-focused prompts produced more unsatisfactory responses and follow-up questions than conceptual prompts • Students used a range of follow-up strategies when initial responses were unsatisfactory • Guidance is needed to help students develop advanced prompting techniques

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 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 score0.316
Threshold uncertainty score0.618

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
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 head0.024
GPT teacher head0.335
Teacher spread0.311 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueGEOMATICASame topicAI in Service InteractionsFrench-language works237,207