cs.HCAug 18, 2026

Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks

Authors: Matin Amoozadeh, Amin Alipour

Organizations: University of Houston Houston, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Background and Context: Question and inquiry are integral parts of knowledge seeking and learning. Despite their importance, students tend not to ask enough questions in the classroom. However, studies have shown that students interact extensively with generative AI systems for learning and problem solving. Objective: In this paper, we seek to better understand the types of questions that students ask AI systems, and how those questions evolve during problem solving and across tasks. Method: We use the Graesser et al. taxonomy to classify students' inquiries into 18 types. We develop a few-shot learning approach to automatically classify students' interactions with AI into these categories. We use this system to analyze 830 interactions of CS2 students across two programming tasks. Findings: Our results suggest that a small subset of question types accounts for the majority of student inquiries, and that the types of questions students ask change substantially as the task progresses.

Figures & tables

CharacteristicSession 1Session 2
 n (%)n (%)
Freshman24 (40.0)17 (45.9)
Sophomore21 (35.0)12 (32.4)
Junior13 (21.7)6 (16.2)
Senior2 (3.3)2 (5.4)
Computer Science44 (73.3)32 (86.5)
Table 1. Participant Characteristics by Session
CategoryDefinitionExample (Programming Context)
VerificationAsks whether a statement or condition is true or falseIs this constructor required?
DisjunctiveAsks which of multiple alternatives is correctShould this be public or protected?
Concept CompletionRequests missing information needed to complete a conceptWhat is the return type of this function?
Feature SpecificationAsks about properties, attributes, or components of an entityWhat data members should this class have?
QuantificationRequests numerical or quantitative informationHow many parameters does this function take?
DefinitionAsks for the meaning of a concept or termWhat does protected mean?
Table 2. Graesser et al ( Graesser and Person, 1994 ) Question Categories
Figure 1. Frequency of types of questions in Session 1 and Session 2.
 Session 1Session 2
CategoryNNQuestionsNNQuestions
All Students6043237398
Continuing-Gen.3427117239
First-Gen.2616120159
Avg. Questions per Student (Mean ±\pm SD)
All Students 7.20 10.76
Table 3. Question Dataset Summary by Session and Generation Status
Figure 2. Mean difference in Graesser question-type usage between continuing-generation and first-generation students across both sessions. Positive values indicate higher usage by continuing-generation students. An asterisk (*) denotes statistical significance at p<.05p<.05 .
Figure 3. State-transition diagram of Graesser question types in Session 1 ( N=60N=60 students, 432 prompts).
Figure 4. State-transition diagram of Graesser question types in Session 2 ( N=37N=37 students, 398 prompts).
More in this topic

Few-Shot Text Classification

See all 9 papers

Explore similar work

CardsList

  1. Unpacking Vibe Coding: Help-Seeking Processes in Student-AI Interactions While Programming

    Apr 29, 2026Daiana Rinja, Eduardo Araujo Oliveira, Sonsoles López-Pernas +3AI in EducationProgramming Education

    CATALPA, FernUniversität in Hagen, 58097 Hagen, Germany · School of Computing and Information Systems, University of Melbourne, Parkville VIC 3010, Australia · School of Computing, University of Eastern Finland, 80110 Joensuu, Finland

  2. Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs

    Jun 9, 2026Youssef Medhat, Junsoo Park, Ploy Thajchayapong +1AI in EducationEducational Data Mining

    Georgia Institute of Technology, Atlanta, GA, USA

  3. Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications

    Jul 12, 2026Nasser Giacaman, Valerio Terragni, Paul Denny +1Computer Science EducationCode Generation

    University of Auckland · Auckland, New Zealand · University of New South Wales +1