Works (55)

Updated: July 18th, 2024 05:03

2024 article

Example, nudge, or practice? Assessing metacognitive knowledge transfer of factual and procedural learners

Abdelshiheed, M., Moulder, R., Hostetter, J. W., Barnes, T., & Chi, M. (2024, July 1). USER MODELING AND USER-ADAPTED INTERACTION, Vol. 7.

By: M. Abdelshiheed, R. Moulder, J. Hostetter, T. Barnes & M. Chi

author keywords: Knowledge transfer; Metacognitive knowledge; Factual knowledge; Procedural knowledge; Conditional knowledge
Sources: Web Of Science, NC State University Libraries
Added: July 17, 2024

2024 article

Toward a More Diverse and Equitable Food Distribution System: Amplifying Diversity, Equity and Inclusion in Food Bank Operations

Hamilton, M., Morrow, B. F., Davis, L. B., Morgan, S., Ivy, J. S., Jiang, S., … Hilliard, K. (2024, May 17). PRODUCTION AND OPERATIONS MANAGEMENT.

By: M. Hamilton*, B. Morrow*, L. Davis*, S. Morgan*, J. Ivy*, S. Jiang*, M. Chi n, K. Hilliard*

author keywords: Food insecurity; hunger relief; culturally relevant food; equity
Source: Web Of Science
Added: June 3, 2024

2023 journal article

Healthful Connected Living: Vision and Challenges for the Case of Obesity

IEEE INTERNET COMPUTING, 27(3), 7–14.

By: M. Singh n, M. Chi n & V. Misra n

author keywords: Sensors; Obesity; Heart rate variability; Biomedical monitoring; Artificial intelligence; Temperature measurement; Psychology
UN Sustainable Development Goal Categories
Sources: Web Of Science, ORCID, NC State University Libraries
Added: May 11, 2023

2023 journal article

How and When: The Impact of Metacognitive Knowledge Instruction and Motivation on Transfer Across Intelligent Tutoring Systems

International Journal of Artificial Intelligence in Education, 9.

By: M. Abdelshiheed n, T. Barnes n & M. Chi n

author keywords: Metacognitive knowledge; Motivation; Metacognitive interventions; Transfer; Intelligent tutoring systems
TL;DR: A framework suggests that the key factors for facilitating transfer are the motivation for StrBoth students, nudges for their StrHow peers, and the combination of worked examples and nudges for Rote students. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Sources: Web Of Science, ORCID, NC State University Libraries, Crossref
Added: October 23, 2023

2023 journal article

Investigating the Impact of Backward Strategy Learning in a Logic Tutor: Aiding Subgoal Learning Towards Improved Problem Solving

International Journal of Artificial Intelligence in Education, 8.

By: P. Shabrina n, B. Mostafavi n, M. Abdelshiheed n, M. Chi n & T. Barnes n

author keywords: Subgoal; Logic tutor; Intelligent tutor systems; Backward strategy; Forward strategy
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Sources: Web Of Science, ORCID, NC State University Libraries, Crossref
Added: September 5, 2023

2023 article proceedings

Latent Space Encoding for Interpretable Fuzzy Logic Rules in Continuous and Noisy High-Dimensional Spaces

Presented at the 2023 IEEE International Conference on Fuzzy Systems (FUZZ).

By: J. Hostetter n & M. Chi n

Event: 2023 IEEE International Conference on Fuzzy Systems (FUZZ)

TL;DR: The efficacy of the proposed method is showcased through its application in predicting the acceleration of one of the links for the Unimation Puma 560 robot arm, effectively overcoming the challenges posed by non-linearity and noise in the dataset. (via Semantic Scholar)
Sources: Web Of Science, Crossref
Added: February 12, 2024

2023 article proceedings

Leveraging Fuzzy Logic Towards More Explainable Reinforcement Learning-Induced Pedagogical Policies on Intelligent Tutoring Systems

Presented at the 2023 IEEE International Conference on Fuzzy Systems (FUZZ).

By: J. Hostetter n, M. Abdelshiheed n, T. Barnes n & M. Chi n

Event: 2023 IEEE International Conference on Fuzzy Systems (FUZZ)

TL;DR: F fuzzy logic is applied to distill knowledge from Deep RL-induced policies into interpretable IF-THEN Fuzzy Logic Controller (FLC) rules, showing that these FLC policies significantly outperform expert policy and student decisions, demonstrating the effectiveness of this approach. (via Semantic Scholar)
Sources: Web Of Science, Crossref, NC State University Libraries
Added: December 6, 2023

2023 journal article

TC-DTW: Accelerating multivariate dynamic time warping through triangle inequality and point clustering

INFORMATION SCIENCES, 621, 611–626.

By: D. Shen* & M. Chi n

TL;DR: A solution that, for the first time, consistently outperforms the classic multivariate DTW algorithm across dataset sizes, series lengths, data dimensions, temporal window sizes, and machines is presented. (via Semantic Scholar)
Source: Web Of Science
Added: January 17, 2023

2023 article

Time-aware deep reinforcement learning with multi-temporal abstraction

Kim, Y. J., & Chi, M. (2023, March 25). APPLIED INTELLIGENCE.

By: Y. Kim n & M. Chi n

author keywords: Time-aware; Temporal abstraction; Deep reinforcement learning; Irregular time series; RL for real-world applications; Nuclear reactor control; Sepsis treatment
TL;DR: T-MTA significantly outperforms competing baseline frameworks, including a standalone Time-aware DRL framework, MTAs, and the original DRL methods without considering either type of temporal aspect, especially when partially observable environments are involved and the range of time intervals is large. (via Semantic Scholar)
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: April 11, 2023

2023 conference paper

XAI to Increase the Effectiveness of an Intelligent Pedagogical Agent

Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents. (IVA’23). Presented at the 23rd ACM International Conference on Intelligent Virtual Agents. (IVA’23), Würzburg, Germany.

By: J. Hostetter n, C. Conati*, X. Yang n, M. Abdelshiheed n, T. Barnes n & M. Chi n

Event: 23rd ACM International Conference on Intelligent Virtual Agents. (IVA’23) at Würzburg, Germany on September 19-22, 2023

TL;DR: Empirical study shows the IPA with personalized explanations significantly improves students' learning outcomes compared to the other versions of the Intelligent Pedagogical Agent. (via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries, NC State University Libraries, ORCID
Added: December 17, 2023

2022 article

Enhancing a student productivitymodel for adaptive problem-solving assistance

Maniktala, M., Chi, M., & Barnes, T. (2022, August 3). USER MODELING AND USER-ADAPTED INTERACTION.

By: M. Maniktala n, M. Chi n & T. Barnes n

author keywords: Adaptive support; Student modeling; Assistance dilemma; Unproductivity; Data-driven tutoring; Propositional logic
TL;DR: A novel data-driven approach to incorporate students’ hint usage in predicting their need for help that significantly improves the adaptive hint policy’s efficacy in predictingStudents’ HelpNeed, thereby reducing training unproductivity, reducing possible help avoidance, and increasing possible help appropriateness. (via Semantic Scholar)
Source: Web Of Science
Added: August 15, 2022

2022 chapter book

Mixing Backward- with Forward-Chaining for Metacognitive Skill Acquisition and Transfer

By: M. Abdelshiheed n, J. Hostetter n, X. Yang n, T. Barnes n & M. Chi n

Event: Springer International Publishing

author keywords: Strategy awareness; Time awareness; Metacognitive skill instruction; Preparation for future learning; Backward chaining
TL;DR: This work investigated the impact of mixing BC with FC on teaching strategy- and time-awareness for nonStrTime students and showed that on both tutors, Exp outperformed Ctrl and caught up with StrTime. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Sources: Web Of Science, ORCID, NC State University Libraries, Crossref
Added: November 21, 2022

2022 article

Reconstructing Missing EHRs Using Time-Aware Within- and Cross-Visit Information for Septic Shock Early Prediction

2022 IEEE 10TH INTERNATIONAL CONFERENCE ON HEALTHCARE INFORMATICS (ICHI 2022), pp. 151–162.

By: G. Gao n, F. Khoshnevisan* & M. Chi n

author keywords: Electronic Health Records(EHRs); EHRs Imputation; Septic Shock Early Prediction
TL;DR: A Time-Aware Dual-Cross-Visit missing value imputation method, named TA-DualCV, which spontaneously leverages multivariate dependencies across features and longitudinal dependencies both within- and cross-visit to maximize the information extracted from limited observable records in EHRs. (via Semantic Scholar)
Source: Web Of Science
Added: October 31, 2022

2022 article

Student-Tutor Mixed-Initiative Decision-Making Supported by Deep Reinforcement Learning

ARTIFICIAL INTELLIGENCE IN EDUCATION, PT I, Vol. 13355, pp. 440–452.

By: S. Ju n, . Yang n, T. Barnes n & M. Chi n

author keywords: Critical decisions; Reinforcement learning; Student choice
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: November 21, 2022

2022 article

The Impact of Batch Deep Reinforcement Learning on Student Performance: A Simple Act of Explanation Can Go A Long Way

Ausin, M. S., Maniktala, M., Barnes, T., & Chi, M. (2022, November 28). INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION.

By: M. Ausin n, M. Maniktala n, T. Barnes n & M. Chi n

author keywords: Deep reinforcement learning; Pedagogical policy; Explanation
TL;DR: The results suggest that pairing simple explanations with the Batch DRL policy with explanations can be an important and effective technique for applying RL to real-life, human-centric tasks. (via Semantic Scholar)
Sources: Web Of Science, ORCID
Added: November 29, 2022

2021 journal article

A Theoretical and Evidence-Based Conceptual Design of MetaDash: An Intelligent Teacher Dashboard to Support Teachers' Decision Making and Students’ Self-Regulated Learning

Frontiers in Education, 6.

author keywords: self-regulated learning (SRL); teacher decision making; learning; multimodal data; teacher dashboards
TL;DR: A conceptual system design for integrating reinforcement learning into a teacher dashboard to help guide the utilization of multimodal data collected on students’ and teachers’ CAMM SRL processes during complex learning. (via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries, Crossref
Added: August 23, 2021

2021 article

Avoiding Help Avoidance: Using Interface Design Changes to Promote Unsolicited Hint Usage in an Intelligent Tutor (September, 10.1007/s40593-020-00213-3, 2020)

Maniktala, M., Cody, C., Barnes, T., & Chi, M. (2021, March). INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION, Vol. 31, pp. 154–155.

By: M. Maniktala n, C. Cody n, T. Barnes n & M. Chi n

Source: Web Of Science
Added: December 21, 2020

2021 article

Data to Donations: Towards In-Kind Food Donation Prediction across Two Coasts

2021 IEEE GLOBAL HUMANITARIAN TECHNOLOGY CONFERENCE (GHTC), pp. 281–288.

By: E. Sharma n, L. Davis*, J. Ivy n & M. Chi n

author keywords: Food Insecurity; Humanitarian Supply Chain; Bayesian Structural Time Series; Long Short Term Memory; Training Length; Expanding and Sliding Window
TL;DR: This work investigates the effectiveness of employing an average of all predictions formed by considering all three factors at both monthly and weekly levels for both food banks and shows that this average of predictions significantly and consistently outperforms all classical models, deep learning, and BSTS. (via Semantic Scholar)
UN Sustainable Development Goal Categories
14. Life Below Water (OpenAlex)
Source: Web Of Science
Added: March 28, 2022

2021 chapter book

Evaluating Critical Reinforcement Learning Framework in the Field

By: S. Ju n, G. Zhou n, M. Abdelshiheed n, T. Barnes n & M. Chi n

Event: Springer International Publishing

author keywords: Critical decisions; Reinforcement learning; ITS
Sources: Web Of Science, ORCID, NC State University Libraries, Crossref
Added: November 28, 2022

2021 article

InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem

2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp. 1337–1348.

By: M. Ausin n, H. Azizsoltani n, S. Ju n, Y. Kim n & M. Chi n

author keywords: Credit Assignment Problem; Deep Reinforcement Learning
TL;DR: The results show that InferNet is robust to delayed or noisy reward functions, and it could be used effectively for solving the temporal CAP in a wide range of RL tasks, when immediate rewards are not available or they are noisy. (via Semantic Scholar)
Source: Web Of Science
Added: July 5, 2022

2021 article

Leveraging Granularity: Hierarchical Reinforcement Learning for Pedagogical Policy Induction

Zhou, G., Azizsoltani, H., Ausin, M. S., Barnes, T., & Chi, M. (2021, August 16). INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION, Vol. 8.

By: G. Zhou n, H. Azizsoltani n, M. Ausin n, T. Barnes n & M. Chi n

author keywords: Hierarchical reinforcement learning; Decision granularity; Pedagogical policy
TL;DR: An offline, off-policy Gaussian Processes based Hierarchical Reinforcement Learning (HRL) framework is proposed and applied to induce a hierarchical pedagogical policy that makes adaptive, effective decisions at both the problem and step levels. (via Semantic Scholar)
Sources: Web Of Science, NC State University Libraries
Added: August 23, 2021

2021 article

Multi-Temporal Abstraction with Time-Aware Deep Q-Learning for Septic Shock Prevention

2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp. 1657–1663.

By: Y. Kim n, M. Ausin n & M. Chi n

author keywords: deep reinforcement learning; time-aware; temporal abstraction; sepsis
TL;DR: This work proposes MTA-TQN, a Multi-view -Temporal Abstraction mechanism within a Time-aware deep Q-learning Network framework for septic shock prevention and demonstrates that both time-awareness and multi-view temporal abstraction are essential to induce effective policies, particularly with irregular time-series data. (via Semantic Scholar)
UN Sustainable Development Goal Categories
3. Good Health and Well-being (OpenAlex)
Source: Web Of Science
Added: July 5, 2022

2021 article

Tackling the Credit Assignment Problem in Reinforcement Learning-Induced Pedagogical Policies with Neural Networks

ARTIFICIAL INTELLIGENCE IN EDUCATION (AIED 2021), PT I, Vol. 12748, pp. 356–368.

By: M. Ausin n, M. Maniktala n, T. Barnes n & M. Chi n

author keywords: Pedagogical agent; Credit assignment problem; Deep reinforcement learning
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Sources: Web Of Science, ORCID
Added: June 16, 2021

2021 article

The Impact of Looking Further Ahead: A Comparison of Two Data-driven Unsolicited Hint Types on Performance in an Intelligent Data-driven Logic Tutor

Cody, C., Maniktala, M., Lytle, N., Chi, M., & Barnes, T. (2021, May 21). INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION.

By: C. Cody n, M. Maniktala n, N. Lytle n, M. Chi n & T. Barnes n

author keywords: Tutoring system; Hints; Assistance; Data-driven methods
TL;DR: The influence of data-driven hint type, Waypoints versus Next-Step hints, on student learning in a logic proof tutoring system, Deep Thought, in a discrete mathematics course is investigated to suggest that Waypoint hints could be beneficial, but more scaffolding may be needed to help students follow them. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Source: Web Of Science
Added: June 10, 2021

2021 article

To Reduce Healthcare Workload: Identify Critical Sepsis Progression Moments through Deep Reinforcement Learning

2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp. 1640–1646.

By: S. Ju n, Y. Kim n, M. Ausin n, M. Mayorga n & M. Chi n

author keywords: Reinforcement Learning; Sepsis; Critical Decision
TL;DR: The Critical-DRL approach, by which decisions are made at critical junctures, is as effective as a fully executed DRL policy and moreover, it enables the critical moments in the septic treatment process, thus greatly reducing burden on medical decision-makers by allowing them to make critical clinical decisions without negatively impacting outcomes. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science)
16. Peace, Justice and Strong Institutions (OpenAlex)
Sources: Web Of Science, NC State University Libraries
Added: July 5, 2022

2021 article

Unifying Domain Adaptation and Domain Generalization for Robust Prediction Across Minority Racial Groups

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, Vol. 12975, pp. 521–537.

By: F. Khoshnevisan* & M. Chi n

author keywords: Domain adaptation; Domain generalization; Cross-racial transfer; Septic shock
TL;DR: A multi-source adversarial domain separation framework designed to address two types of discrepancies, covariate shift stemming from differences in patient populations, and systematic bias on account of data collection procedures across medical systems are presented. (via Semantic Scholar)
UN Sustainable Development Goal Categories
10. Reduced Inequalities (OpenAlex)
Source: Web Of Science
Added: November 15, 2021

2020 article

An Adversarial Domain Separation Framework for Septic Shock Early Prediction Across EHR Systems

2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp. 64–73.

By: F. Khoshnevisan n & M. Chi n

author keywords: adversarial domain adaptation variational RNN; Electronic health Record; septic shock; early prediction
TL;DR: By separating globally-shared from domain-specific representations, this framework significantly improves septic shock early prediction performance in both EHRs and outperforms the current state-of-the-art DA models. (via Semantic Scholar)
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: July 26, 2021

2020 article

An Initial Study on Adapting DTW at Individual Query for Electrocardiogram Analysis

ADVANCED ANALYTICS AND LEARNING ON TEMPORAL DATA, AALTD 2019, Vol. 11986, pp. 213–228.

By: D. Shen & M. Chi n

author keywords: DTW; Time series analytics; Algorithm optimizations; Electrocardiogram
TL;DR: Experiments on ECG temporal sequences show that the techniques help significantly reduce risks that windowed DTW algorithms are subject to and at the same time keeping a high speed. (via Semantic Scholar)
Source: Web Of Science
Added: June 21, 2021

2020 journal article

Avoiding Help Avoidance: Using Interface Design Changes to Promote Unsolicited Hint Usage in an Intelligent Tutor

INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE IN EDUCATION, 30(4), 637–667.

By: M. Maniktala n, C. Cody n, T. Barnes n & M. Chi n

author keywords: Intelligent tutoring system; Help avoidance; User experience; Unsolicited hints; Aptitude-treatment interaction; Logic proofs; Productive persistence; Clustering; problem solving
TL;DR: Encouraging evidence is provided that hint presentation can significantly impact how students use them and using Assertions can be an effective way to address help avoidance is provided. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Source: Web Of Science
Added: November 9, 2020

2020 journal article

Going deeper: Automatic short-answer grading by combining student and question models

USER MODELING AND USER-ADAPTED INTERACTION, 30(1), 51–80.

By: Y. Zhang n, C. Lin n & M. Chi n

author keywords: Automatic short-answer grading; Machine learning; Deep belief network
TL;DR: Overall, the results on a real-world corpus demonstrate that 1) leveraging student and question models to the conventional answer-based approach can greatly enhance the performance of ASAG, and 2) deep learning models such as DBN can be productively applied to the task of ASAGs. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Web Of Science
Added: March 30, 2020

2020 article

MuLan: Multilevel Language-based Representation Learning for Disease Progression Modeling

2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), pp. 1246–1255.

By: H. Sohn n, K. Park n & M. Chi n

author keywords: Electronic health records; disease progression modeling; interpretability; representation learning
TL;DR: This work presents MuLan: a Multilevel Language-based representation learning framework that can automatically learn a hierarchical representation for EHRs at entry, event, and visit levels and demonstrates that these unified multilevel representations can be utilized for interpreting and visualizing the latent mechanism of patients’ septic shock progressions. (via Semantic Scholar)
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: July 26, 2021

2020 article

PRIME: Block-Wise Missingness Handling for Multi-modalities in Intelligent Tutoring Systems

MULTIMEDIA MODELING (MMM 2020), PT II, Vol. 11962, pp. 63–75.

By: . Yang n, Y. Kim n, M. Taub*, R. Azevedo* & M. Chi n

author keywords: Multimodal; Block-wise missing; Learning gain prediction
TL;DR: 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. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Web Of Science
Added: February 22, 2021

2019 article

Hierarchical Reinforcement Learning for Pedagogical Policy Induction

ARTIFICIAL INTELLIGENCE IN EDUCATION (AIED 2019), PT I, Vol. 11625, pp. 544–556.

By: G. Zhou n, H. Azizsoltani n, M. Ausin n, T. Barnes n & M. Chi n

author keywords: Hierarchical Reinforcement Learning; Pedagogical policies
TL;DR: This paper proposes and applies an offline, off-policy Gaussian Processes based Hierarchical Reinforcement Learning (HRL) framework to induce a hierarchical pedagogical policy that makes decisions at both problem and step levels and shows that the HRL policy is significantly more effective than a Deep Q-Network induced policy and a random yet reasonable baseline policy. (via Semantic Scholar)
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Sources: Web Of Science, NC State University Libraries
Added: December 2, 2019

2018 chapter

Empirically Evaluating the Effectiveness of POMDP vs. MDP Towards the Pedagogical Strategies Induction

In Lecture Notes in Computer Science (pp. 327–331).

By: S. Shen n, B. Mostafavi n, C. Lynch n, T. Barnes n & M. Chi n

author keywords: Reinforcement Learning; POMDP; MDP; ITS
TL;DR: An empirical study where RL-induced policies are compared against a random yet reasonable policy shows that when the contents are controlled to be equal, the MDP-based policy can improve students’ learning significantly more than the random baseline while the POMDP- based policy cannot outperform the later. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Crossref
Added: January 19, 2020

2018 article

Improving Learning & Reducing Time: A Constrained Action-Based Reinforcement Learning Approach

Improving Learning & Reducing Time: A Constrained Action-Based Reinforcement Learning Approach. PROCEEDINGS OF THE 26TH CONFERENCE ON USER MODELING, ADAPTATION AND PERSONALIZATION (UMAP'18), pp. 43–51.

By: S. Shen n, M. Ausin n, B. Mostafavi n & M. Chi n

author keywords: Constrained Reinforcement Learning; POMDP; Intelligent Tutoring System
TL;DR: This work constructs a general data-driven framework called Constrained Action-based Partially Observable Markov Decision Process (CAPOMDP) to induce effective pedagogical policies and induces two types of policies: CAPOMDPLG using learning gain as reward with the goal of improving students' learning performance, and CAPomDPTime using time as reward for reducing students' time on task. (via Semantic Scholar)
UN Sustainable Development Goal Categories
16. Peace, Justice and Strong Institutions (OpenAlex)
Source: Web Of Science
Added: April 2, 2019

2017 chapter

A Comparisons of BKT, RNN and LSTM for Learning Gain Prediction

In Lecture Notes in Computer Science (pp. 536–539).

By: C. Lin n & M. Chi n

author keywords: LSTM; RNN; BKT; Learning gain prediction
TL;DR: Interestingly, it is found that RNN can achieve a reasonably accurate prediction of student final learning gains using only the first 40% of the entire training sequence; using the first 70%" of the sequence would produce a result comparable to using the entire sequence. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Source: Crossref
Added: February 24, 2020

2017 conference paper

A Comparisons of BKT, RNN and LSTM for Learning Gain Prediction

Artificial intelligence in education, aied 2017, 10331, 536–539.

By: C. Lin & M. Chi

Source: NC State University Libraries
Added: August 6, 2018

2017 conference paper

LSTM for septic shock: Adding unreliable labels to reliable predictions

2017 IEEE International Conference on Big Data (Big Data), 1233–1242.

TL;DR: A generic framework to predict septic shock based on Long-Short Term Memory (LSTM) model, which is capable of memorizing temporal dependencies over a long period, is proposed and the robustness of the method is validated using three sets of clinician-proposed adjusted ground-truth labels. (via Semantic Scholar)
Source: NC State University Libraries
Added: August 6, 2018

2016 journal article

A comparison of two methods of active learning in physics: inventing a general solution versus compare and contrast

INSTRUCTIONAL SCIENCE, 44(2), 177–195.

By: D. Chin*, M. Chi n & D. Schwartz*

author keywords: Science education; Science instruction; Inventing; Compare and contrast; Contrasting cases
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Source: Web Of Science
Added: August 6, 2018

2016 conference paper

An analysis of feature selection and reward function for model-based reinforcement learning

Intelligent tutoring systems, its 2016, 0684, 504–505.

Source: NC State University Libraries
Added: August 6, 2018

2016 conference paper

Evolving augmented graph grammars for argument analysis

Proceedings of the 2016 Genetic and Evolutionary Computation Conference (GECCO'16 Companion), 65–66.

By: C. Lynch n, L. Xue n & M. Chi n

TL;DR: The work on the automatic induction of graph grammars for argument diagrams via EC outperforms the existing grammar induction algorithms gSpan and Subdue on the dataset and shows that it is possible to augment the standard EC process to harvest a set of diverse rules which can be filtered via a post-hoc Chi-Squared analysis. (via Semantic Scholar)
Source: NC State University Libraries
Added: August 6, 2018

2016 chapter

Intervention-BKT: Incorporating Instructional Interventions into Bayesian Knowledge Tracing

In Intelligent Tutoring Systems (pp. 208–218).

By: C. Lin n & M. Chi n

author keywords: Knowledge tracing; Hidden Markov Model; Input Output Hidden Markov Model; Student modeling; Instructional intervention
TL;DR: The results showed the new model outperforms conventional BKT and two factor analysis based alternatives: Additive Factor Model AFM and Instructional Factor Model IFM; moreover, the learned parameters of Intervention-BKT can recommend adaptive pedagogical policies. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Source: Crossref
Added: February 24, 2020

2016 conference paper

Intervention-BKT: Incorporating instructional interventions into Bayesian knowledge tracing

Intelligent tutoring systems, its 2016, 0684, 208–218.

By: C. Lin & M. Chi

Source: NC State University Libraries
Added: August 6, 2018

2015 chapter

Data-Driven Worked Examples Improve Retention and Completion in a Logic Tutor

In Lecture Notes in Computer Science (pp. 726–729).

author keywords: Worked examples; Data-driven; Problem-solving
TL;DR: This study demonstrates that worked examples, automatically generated from student data, can be used to improve student learning in tutoring systems. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (Web of Science; OpenAlex)
Source: Crossref
Added: January 19, 2020

2015 conference paper

Data-driven worked examples improve retention and completion in a logic tutor

Artificial intelligence in education, aied 2015, 9112, 726–729.

Source: NC State University Libraries
Added: August 6, 2018

2015 chapter

Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis

In Data and Applications Security and Privacy XXIX (pp. 170–187).

By: E. Choo n, T. Yu n & M. Chi n

author keywords: Opinion spammer groups; Sentiment analysis; Community discovery
TL;DR: The results show that the approach is comparable to the existing state-of-art content-based classifier, meaning that this approach can identify spammer groups reliably even if spammers alter their contents. (via Semantic Scholar)
Source: Crossref
Added: February 24, 2020

2015 conference paper

Detecting opinion spammer groups through community discovery and sentiment analysis

Data and applications security and privacy xxix, 9149, 170–187.

By: E. Choo, T. Yu & M. Chi

Source: NC State University Libraries
Added: August 6, 2018

2014 chapter

Can Diagrams Predict Essay Grades?

In Intelligent Tutoring Systems (pp. 260–265).

By: C. Lynch*, K. Ashley* & M. Chi n

TL;DR: It is shown that manually-assigned diagram grades and automatic structural features of argument diagrams can be used to predict students’ future essay grades, thus supporting the use of argument diagram models for instruction. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Crossref
Added: August 28, 2020

2014 chapter

When Is Tutorial Dialogue More Effective Than Step-Based Tutoring?

In Intelligent Tutoring Systems (pp. 210–219).

By: M. Chi n, P. Jordan* & K. VanLehn*

TL;DR: This paper compares a micro-step based NL-tutoring system that employs induced pedagogical policies, Cordillera, to a well-evaluated step-based ITS, Andes, and concludes that the pairing of effective policies with aMicro- step based system does significantly outperform a step- based system; however, there is no significant difference in the absence ofeffective policies. (via Semantic Scholar)
Source: Crossref
Added: August 28, 2020

2014 conference paper

When is tutorial dialogue more effective than step-based tutoring?

Intelligent tutoring systems, its 2014, 8474, 210–219.

By: M. Chi, P. Jordan & K. VanLehn

Source: NC State University Libraries
Added: August 6, 2018

2011 journal article

Empirically evaluating the application of reinforcement learning to the induction of effective and adaptive pedagogical strategies

User Modeling and User-Adapted Interaction, 21(1-2), 137–180.

By: M. Chi*, K. VanLehn*, D. Litman* & P. Jordan*

author keywords: Reinforcement learning; Pedagogical strategy; Machine learning; Human learning
TL;DR: This paper addresses the technical challenges in applying RL to Cordillera, a Natural Language Tutoring System teaching students introductory college physics and shows that the RL-induced policies improved students’ learning gains significantly. (via Semantic Scholar)
Source: Crossref
Added: August 28, 2020

2010 chapter

Do Micro-Level Tutorial Decisions Matter: Applying Reinforcement Learning to Induce Pedagogical Tutorial Tactics

In Intelligent Tutoring Systems (pp. 224–234).

By: M. Chi*, K. VanLehn* & D. Litman*

TL;DR: Reinforcement Learning was applied to induce two sets of tutorial tactics from pre-existing human interaction data and showed that when the contents were controlled so as to be the same, different pedagogical tutorial tactics would make a difference in learning and more specifically, the NormGain students outperformed their peers. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Crossref
Added: August 28, 2020

2010 chapter

Inducing Effective Pedagogical Strategies Using Learning Context Features

In User Modeling, Adaptation, and Personalization (pp. 147–158).

By: M. Chi*, K. VanLehn*, D. Litman* & P. Jordan*

TL;DR: The results show that RL is a feasible approach to induce effective, adaptive pedagogical strategies by using a relatively small training corpus and believe that this approach can be used to develop other adaptive and personalized learning environments. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Crossref
Added: August 28, 2020

2008 chapter

Eliminating the Gap between the High and Low Students through Meta-cognitive Strategy Instruction

In Intelligent Tutoring Systems (pp. 603–613).

By: M. Chi* & K. VanLehn*

TL;DR: It is shown that an ITS teaching a domain-independent problem-solving strategy indeed closed the gap between High and Low learners, not only in the domain where it was taught (probability) but also in a second domainWhere it was not taught (physics). (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Crossref
Added: August 28, 2020

2004 chapter

Implicit Versus Explicit Learning of Strategies in a Non-procedural Cognitive Skill

In Intelligent Tutoring Systems (pp. 521–530).

By: K. VanLehn*, D. Bhembe*, M. Chi*, C. Lynch*, K. Schulze*, R. Shelby*, L. Taylor*, D. Treacy*, A. Weinstein*, M. Wintersgill*

TL;DR: Two physics tutoring systems are developed, Andes and Pyrenees, where Andes is a model-tracing tutor that teaches a problem solving strategy explicitly, whereas Andes uses a novel pedagogy, developed over many years of use in the field, that provides virtually no explicit strategic instruction. (via Semantic Scholar)
UN Sustainable Development Goal Categories
4. Quality Education (OpenAlex)
Source: Crossref
Added: August 28, 2020

Citation Index includes data from a number of different sources. If you have questions about the sources of data in the Citation Index or need a set of data which is free to re-distribute, please contact us.

Certain data included herein are derived from the Web of Science© and InCites© (2024) of Clarivate Analytics. All rights reserved. You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.