Exploiting Cognitive Structure for Adaptive Learning

Liu, Qi; Tong, Shiwei; Liu, Chuanren; Zhao, Hongke; Chen, Enhong; Ma, Haiping; Wang, Shijin

doi:10.1145/3292500.3330922

Cited by 95 publications

(48 citation statements)

References 32 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reinforcement Learning. Developed from Markov decision processes (MDP) (Sutton and Barto 2018), deep reinforcement learning (DRL) has been proved to be a huge success in many domains, such as games (Mnih et al 2015;Hessel et al 2018), robotics (Kober, Bagnell, and Peters 2013;Haarnoja et al 2018) and recommender systems (Chen et al 2019;Liu et al 2019). Existing methods could be divided into two categories: value-based methods, where policies are indirectly acquired according to the estimated value function, and policy-based methods, where policies are directly parameterized (Sutton et al 2000).…”

Section: Related Workmentioning

confidence: 99%

Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach

Wang

Zhang

Liu

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but is still under exploration. Existing studies either fit the fluctuations of time-series or employ regularization terms to constrain learned tendencies. However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics. To address the problem, in this paper, we propose a Trajectory-based Continuous Control for Crowdfunding (TC3) algorithm to predict the funding progress in crowdfunding. Specifically, actor-critic frameworks are employed to model the relationship between investors and campaigns, where all of the investors are viewed as an agent that could interact with the environment derived from the real dynamics of campaigns. Then, to further explore the in-depth implications of patterns (i.e., typical characters) in funding series, we propose to subdivide them into fast-growing and slow-growing ones. Moreover, for the purpose of switching from different kinds of patterns, the actor component of TC3 is extended with a structure of options, which comes to the TC3-Options. Finally, extensive experiments on the Indiegogo dataset not only demonstrate the effectiveness of our methods, but also validate our assumption that the entire pattern learned by TC3-Options is indeed the U-shaped one.

show abstract

Section: Related Workmentioning

confidence: 99%

Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach

Wang

Zhang

Liu

et al. 2020

AAAI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, the problem of recommending personalised sequences of resources to reach a long-term goal has emerged, but remains less widespread [12,13]. Sequence recommendation is highly different from traditional recommendation [8] as it does not only exploit the temporal ordering for the generation of sequences of resources, but also contribute to reach a goal along the sequence.…”

Section: Learning Path Recommender Systemsmentioning

confidence: 99%

“…As mentioned in [8], the length of the RLP is required by any algorithm. In accordance with the literature, it will be set as the median length of the students' LP in the review period.…”

Section: Dataset and Experimental Setupmentioning

confidence: 99%

“…More and more attention is being paid to these recommenders, that are also called sequence-aware or path recommender systems. In education, recommending a sequence of learning resources is referred to as a Learning Path (LP) recommendation [8,10,22]. When students adopt a recommended LP, they may improve their level of knowledge, increase their chance of success at exams, maintain their motivation, etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

New Measures for Offline Evaluation of Learning Path Recommenders

Zhang

Brun

Boyer

2020

Addressing Global Challenges and Quality Education

View full text Add to dashboard Cite

Recommending students useful and effective learning paths is highly valuable to improve their learning experience. The evaluation of the effectiveness of this recommendation is a challenging task that can be performed online or offline. Online evaluation is highly popular but it relies on actual path recommendations to students, which may have dramatic implications. Offline evaluation relies on static datasets of students' learning activities and simulates paths recommendations. Although easier to run, it is difficult to accurately evaluate offline the effectiveness of a learning path recommendation. To tackle this issue, this work proposes simple offline evaluation measures. We show that they actually allow to characterise and differentiate the algorithms.

show abstract

“…With the recent boom in the development of online intelligent education, such as Massive Open Online Courses (MOOC) [1], Khan Academy, and Online Judging System [2], a large number of applications based on online intelligent education have rapidly moved into a place of prominence in the mind of the public, e.g., exercise recommendation [3], student performance prediction [4] and learning path recommendation [5].…”

Section: Introductionmentioning

confidence: 99%

Tracking Knowledge Structures and Proficiencies of Students With Learning Transfer

et al. 2021

View full text Add to dashboard Cite

In online intelligent education systems, to offer proactive studying services to students (e.g., learning path recommendation), a crucial demand is to track students' knowledge mastery levels over time. However, existing works ignore the impact of learning transfer on knowledge tracing and only track knowledge proficiency. Knowledge proficiency alone cannot fully reflect students' knowledge mastery levels. A student's knowledge structure (the similarities and differences within knowledge concepts) and abstract principle mastery level (common attributes among knowledge concepts, such as learning methods) also need to be tracked. To this end, we propose a novel multilevel Knowledge Tracing model with Learning Transfer (KTLT) to track students' knowledge mastery levels. First, we clarify the relationships among abstract principles, knowledge structure, and knowledge proficiency by utilizing the learning transfer theory in educational psychology. Then, we associate each problem with a knowledge vector in which each element represents an explicit knowledge concept by leveraging educational priors (i.e., a Qmatrix). Correspondingly, each student is represented as a knowledge vector (knowledge proficiency) and an abstract principle vector (abstract principle mastery). Given a student's knowledge and abstract principle vector over time, we use the learning and forgetting curve as priors to capture the student's knowledge proficiency and abstract principle mastery level over time. Furthermore, we embed the knowledge concept by using a student's abstract principle mastery level and obtain a personalized knowledge relevance matrix (a student's knowledge structure) by calculating the cosine similarity among the knowledge embedding results. Finally, we design a probabilistic matrix factorization framework by combining student and problem priors for tracking a student's knowledge mastery. Extensive experiments on two real-world datasets demonstrate both the effectiveness and explanatory ability of the KTLT. INDEX TERMS Knowledge tracing; learning transfer; data mining; education priors; dynamic modeling; probability graph model.

show abstract

Exploiting Cognitive Structure for Adaptive Learning

Cited by 95 publications

References 32 publications

Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach

Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach

New Measures for Offline Evaluation of Learning Path Recommenders

Tracking Knowledge Structures and Proficiencies of Students With Learning Transfer

Contact Info

Product

Resources

About