Chatbot Development as a Digital Learning Tool to Increase Students’ Research Knowledge
Bibliographic record
Abstract
The research aimed to: 1) develop the chatbot; 2) evaluate its effectiveness; and 3) investigate its effects on students’ research knowledge. The sample consisted of 36 Thai university students. The research instruments consisted of: 1) the chatbot; 2) an evaluation form; 3) an effectiveness questionnaire; and 4) research tests. Data analysis used was mean, standard deviation, content analysis and a t-test. The findings indicated that: 1) the chatbot was evaluated by experts with the applicability at a very high level ( = 4.67, S.D. = 0.08) with recommendation to add more research content and interactive learning. The pilot test was done with 14 non-target group of students. Students perceived the chatbot’s effectiveness at a high level ( = 4.43, S.D. = 0.35) with comments to add more examples and graphics to make the chatbot more interesting; 2) the 36 target group of Thai university students perceived the chatbot as an effective technology to use as a digital learning tool at a high level ( = 4.37, S.D. = 0.48). They thought that chatbot technology was easy to use, easy to understand, innovative and fun for learning. They could get answers instantly and be able to seek specific information without waiting for responses. However, in response to questions not matched keywords specified, further details of finding proper answers such as links should be provided instead of leaving those questions unanswered. Also, the chatbot only provided responses when typing correctly so there should be an option to choose from a list of questions or keywords; and 3) the post-test scores were significantly higher than the pre-test scores at the 0.05 level of significance. In conclusion, using chatbot technology in education settings to increase students’ research knowledge gave positive results as it led to positive learning outcomes and helped provide better personalized learning experience for students.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.024 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".