@inproceedings{hostetter_conati_yang_abdelshiheed_barnes_chi_2023, place={Germany}, title={XAI to Increase the Effectiveness of an Intelligent Pedagogical Agent}, url={https://doi.org/10.1145/3570945.3607301}, DOI={10.1145/3570945.3607301}, abstractNote={We explore eXplainable AI (XAI) to enhance user experience and understand the value of explanations in AI-driven pedagogical decisions within an Intelligent Pedagogical Agent (IPA). Our real-time and personalized explanations cater to students' attitudes to promote learning. In our empirical study, we evaluate the effectiveness of personalized explanations by comparing three versions of the IPA: (1) personalized explanations and suggestions, (2) suggestions but no explanations, and (3) no suggestions. Our results show the IPA with personalized explanations significantly improves students' learning outcomes compared to the other versions.}, booktitle={Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents. (IVA’23)}, author={Hostetter, J.W. and Conati, C. and Yang, X. and Abdelshiheed, M. and Barnes, T. and Chi, M.}, year={2023} }
 @misc{abdelshiheed_hostetter_yang_barnes_chi_2022, title={Mixing Backward- with Forward-Chaining for Metacognitive Skill Acquisition and Transfer}, volume={13355}, ISBN={9783031116438 9783031116445}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-031-11644-5_47}, DOI={10.1007/978-3-031-11644-5_47}, abstractNote={Metacognitive skills have been commonly associated with preparation for future learning in deductive domains. Many researchers have regarded strategy- and time-awareness as two metacognitive skills that address how and when to use a problem-solving strategy, respectively. It was shown that students who are both strategy- and time-aware (StrTime) outperformed their nonStrTime peers across deductive domains. In this work, students were trained on a logic tutor that supports a default forward-chaining (FC) and a backward-chaining (BC) strategy. We investigated the impact of mixing BC with FC on teaching strategy- and time-awareness for nonStrTime students. During the logic instruction, the experimental students (Exp) were provided with two BC worked examples and some problems in BC to practice how and when to use BC. Meanwhile, their control (Ctrl) and StrTime peers received no such intervention. Six weeks later, all students went through a probability tutor that only supports BC to evaluate whether the acquired metacognitive skills are transferred from logic. Our results show that on both tutors, Exp outperformed Ctrl and caught up with StrTime.}, journal={Lecture Notes in Computer Science}, publisher={Springer International Publishing}, author={Abdelshiheed, Mark and Hostetter, John Wesley and Yang, Xi and Barnes, Tiffany and Chi, Min}, year={2022}, pages={546–552} }
 @article{ju_yang_barnes_chi_2022, title={Student-Tutor Mixed-Initiative Decision-Making Supported by Deep Reinforcement Learning}, volume={13355}, ISBN={["978-3-031-11643-8"]}, ISSN={["1611-3349"]}, DOI={10.1007/978-3-031-11644-5_36}, abstractNote={One fundamental goal of education is to enable students to act independently in the world by continuously adapting and learning. Certain learners are less sensitive to learning environments and can always perform well, while others are more sensitive to variations in learning environments and may fail to learn. We refer to the former as high performers and the latter as low performers. Previous research showed that low performers benefit more from tutor-driven Intelligent Tutoring Systems (ITSs), in which the tutor makes pedagogical decisions, while the high ones often prefer to take control of their own learning by making decisions by themselves. We propose a student-tutor mixed-initiative (ST-MI) decision-making framework which balances allowing students some control over their own learning while ensuring effective pedagogical interventions. In an empirical study, ST-MI significantly improved student learning gains than an Expert-designed, tutor-driven pedagogical policy on an ITS. Furthermore, our ST-MI framework was found to offer low performers the same benefits as the Expert policy, while that for high performers was significantly greater than the Expert policy.}, journal={ARTIFICIAL INTELLIGENCE IN EDUCATION, PT I}, author={Ju, Song and Yang, Xi and Barnes, Tiffany and Chi, Min}, year={2022}, pages={440–452} }
 @article{yang_kim_taub_azevedo_chi_2020, title={PRIME: Block-Wise Missingness Handling for Multi-modalities in Intelligent Tutoring Systems}, volume={11962}, ISBN={["978-3-030-37733-5"]}, ISSN={["1611-3349"]}, DOI={10.1007/978-3-030-37734-2_6}, abstractNote={Block-wise missingness in multimodal data poses a challenging barrier for the analysis over it, which is quite common in practical scenarios such as the multimedia intelligent tutoring systems (ITSs). In this work, we collected data from 194 undergraduates via a biology ITS which involves three modalities: student-system logfiles, facial expressions, and eye tracking. However, only 32 out of the 194 students had all three modalities and 83% of them were missing the facial expression data, eye tracking data, or both. To handle such a block-wise missing problem, we propose a Progressively Refined Imputation for Multi-modalities by auto-Encoder (PRIME), which trains the model based on single, pairwise, and entire modalities for imputation in a progressive manner, and therefore enables us to maximally utilize all the available data. We have evaluated PRIME against single-modality log-only (without missingness handling) and five state-of-the-art missing data handling methods on one important yet challenging student modeling task: to predict students' learning gains. Our results show that using multimodal data as a result of missing data handling yields better prediction performance than using logfiles only, and PRIME outperforms other baseline methods for both learning gain prediction and data reconstruction tasks.}, journal={MULTIMEDIA MODELING (MMM 2020), PT II}, author={Yang, Xi and Kim, Yeo-Jin and Taub, Michelle and Azevedo, Roger and Chi, Min}, year={2020}, pages={63–75} }