Students rated the tutor 3.4 out of 5 overall and particularly liked the worked-out solution feedback¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In a 2011 questionnaire study (40 respondents), the average of the first seven satisfaction questions was 3.4 out of 5, with the highest-scoring item being the usefulness of seeing the complete solution (4.25). → Gerdes 2016

Evidence¶

Gerdes 2016¶

Gerdes, A., Heeren, B., Jeuring, J., & van Binsbergen, L. T. (2016). Ask-Elle: an Adaptable Programming Tutor for Haskell Giving Automated Feedback. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-015-0080-x

q2 · i? · design · r2

Questionnaire administered to 40 students after two tutoring sessions in a functional programming course with over 200 students at Utrecht University (September 2011). "The average of the first seven question gives an overall score of the tutor of 3.4 out of 5." Table 1 shows the complete-solution item scored 4.25 and step-size correspondence scored 2.85.

"The average of the first seven question gives an overall score of the tutor of 3.4 out of 5. This is sufficient, but there is clearly room for improvement."

Discussion¶

Related Claims¶

• In an 18-participant user study, the system received a 4.00/5 overall recommendation, with hallucination resistance rated 4.44/5 and highest ratings for ease of starting a conversation (4.39/5) and response relevance and accuracy (4.06/5) — related
• Students rated the flipped-learning component highest and the GenAI module lower, with GenAI rated stronger for ideation than for time saving or direct output use — related
• In log analysis of 3466 interactions, 56.1% of interactions and 46.3% of attempts were recognised as correct model solutions