skip to main content

Search for: All records

Award ID contains: 1755910

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Knowledge Tracing (KT), which aims to model student knowledge level and predict their performance, is one of the most important applications of user modeling. Modern KT approaches model and maintain an up-to-date state of student knowledge over a set of course concepts according to students’ historical performance in attempting the problems. However, KT approaches were designed to model knowledge by observing relatively small problem-solving steps in Intelligent Tutoring Systems. While these approaches were applied successfully to model student knowledge by observing student solutions for simple problems, such as multiple-choice questions, they do not perform well for modeling complex problem solving in students. Most importantly, current models assume that all problem attempts are equally valuable in quantifying current student knowledge. However, for complex problems that involve many concepts at the same time, this assumption is deficient. It results in inaccurate knowledge states and unnecessary fluctuations in estimated student knowledge, especially if students guess the correct answer to a problem that they have not mastered all of its concepts or slip in answering the problem that they have already mastered all of its concepts. In this paper, we argue that not all attempts are equivalently important in discovering students’ knowledge state, andmore »some attempts can be summarized together to better represent student performance. We propose a novel student knowledge tracing approach, Granular RAnk based TEnsor factorization (GRATE), that dynamically selects student attempts that can be aggregated while predicting students’ performance in problems and discovering the concepts presented in them. Our experiments on three real-world datasets demonstrate the improved performance of GRATE, compared to the state-of-the-art baselines, in the task of student performance prediction. Our further analysis shows that attempt aggregation eliminates the unnecessary fluctuations from students’ discovered knowledge states and helps in discovering complex latent concepts in the problems.« less
  2. The state of the art knowledge tracing approaches mostly model student knowledge using their performance in assessed learning resource types, such as quizzes, assignments, and exercises, and ignore the non-assessed learning resources. However, many student activities are non-assessed, such as watching video lectures, participating in a discussion forum, and reading a section of a textbook, all of which potentially contributing to the students' knowledge growth. In this paper, we propose the  first novel deep learning based knowledge tracing model (DMKT) that explicitly model student's knowledge transitions over both assessed and non-assessed learning activities. With DMKT we can discover the underlying latent concepts of each non-assessed and assessed learning material and better predict the student performance in future assessed learning resources. We compare our proposed method with various state of the art knowledge tracing methods on four real-world datasets and show its effectiveness in predicting student performance, representing student knowledge, and discovering the underlying domain model.
  3. Modern online learning platforms offer a wealth of learning content while leaving the choice of content for study and practice to the learner. Recent work has demonstrated that many students use inefficient learning strategies that lead to lower performance in this context. The ability to detect inefficient learning behavior by monitoring learning data opens a way to timely intervention that could lead to better learning and performance. In this work, we propose SB-DNMF, a structure-based discriminative non-negative matrix factorization model aimed to distinguish between common and distinct learning behavior patterns of low- and high-learning gain students. Our model can discover latent groups of students' behavioral micro-patterns while accounting for the structural similarities between these micro-patterns based upon a weighted edit-distance measure. Our experiments demonstrate that SB-DNMF can find meaningful latent factors that are associated with students' learning gain and can cluster the behavioral patterns into common (trait), and performance-related groups.
  4. The success of cross-domain recommender systems in capturing user interests across multiple domains has recently brought much attention to them. These recommender systems aim to improve the quality of suggestions and defy the cold-start problem by transferring information from one (or more) source domain(s) to a target domain. However, most cross-domain recommenders ignore the sequential information in user history. They only rely on an aggregate or snapshot of user feedback in the past. Most importantly, they do not explicitly model how users transition from one domain to another domain as users continue to interact with different item domains. In this paper, we argue that between-domain transitions in user sequences are useful in improving recommendation quality, dealing with the cold-start problem, and revealing interesting aspects of how user interests transform from one domain to another. We propose TransCrossCF, transition-based cross-domain collaborative filtering, that can capture both within and between domain transitions of user feedback sequences while understanding the relationship between different item types in different domains. Specifically, we model each purchase of a user as a transition from his/her previous item to the next one, under the effect of item domains and user preferences. Our intensive experiments demonstrate that TransCrossCF outperformsmore »the state-of-the-art methods in recommendation task on three real-world datasets, both in the cold-start and hot-start scenarios. Moreover, according to our context analysis evaluations, the between-domain relations captured by TransCrossCF are interpretable and intuitive.« less
  5. Students acquire knowledge as they interact with a variety of learning materials, such as video lectures, problems, and discussions. Modeling student knowledge at each point during their learning period and understanding the contribution of each learning material to student knowledge are essential for detecting students’ knowledge gaps and recommending learning materials to them. Current student knowledge modeling techniques mostly rely on one type of learning material, mainly problems, to model student knowledge growth. These approaches ignore the fact that students also learn from other types of material. In this paper, we propose a student knowledge model that can capture knowledge growth as a result of learning from a diverse set of learning resource types while unveiling the association between the learning materials of different types. Our multi-view knowledge model (MVKM) incorporates a flexible knowledge increase objective on top of a multi-view tensor factorization to capture occasional forgetting while representing student knowledge and learning material concepts in a lower-dimensional latent space. We evaluate our model in different experiments to show that it can accurately predict students’ future performance, differentiate between knowledge gain in different student groups and concepts, and unveil hidden similarities across learning materials of different types.
  6. Recent studies have shown that students follow stable behavioral patterns while learning in online educational systems. These behavioral patterns can further be used to group the students into different clusters. However, as these clusters include both high- and low-performance students, the relation between the behavioral patterns and student performance is yet to be clarified. In this work, we study the relationship between students’ learning behaviors and their performance, in a self-organized online learning system that allows them to freely practice with various problems and worked examples. We represent each student’s behavior as a vector of highsupport sequential micro-patterns. Then, we discover both the prevalent behavioral patterns in each group and the shared patterns across groups using discriminative non-negative matrix factorization. Our experiments show that we can successfully detect such common and specific patterns in students’ behavior that can be further interpreted into student learning behavior trait patterns and performance patterns.
  7. Recent studies of student problem-solving behavior have shown stable behavior patterns within student groups. In this work, we study patterns of student behavior in a richer self-organized practice context where student worked with a combination of problems to solve and worked examples to study. We model student behavior in the form of vectors of micro-patterns and examine student behavior stability in various ways via these vectors. To discover and examine global behavior patterns associated with groups of students, we cluster students according to their behavior patterns and evaluate these clusters in accordance with student performance.
  8. Cross-domain collaborative filtering recommenders exploit data from other domains (e.g., movie ratings) to predict users’ interests in a different target domain (e.g., suggest music). Most current cross-domain recommenders focus on modeling user ratings but pay limited attention to user reviews. Additionally, due to the complexity of these recommender systems, they cannot provide any information to users to support user decisions. To address these challenges, we propose Deep Hybrid Cross Domain (DHCD) model, a cross-domain neural framework, that can simultaneously predict user ratings, and provide useful information to strengthen the suggestions and support user decision across multiple domains. Specifically, DHCD enhances the predicted ratings by jointly modeling two crucial facets of users’ product assessment: ratings and reviews. To support decisions, it models and provides natural review-like sentences across domains according to user interests and item features. This model is robust in integrating user rating and review information from more than two domains. Our extensive experiments show that DHCD can significantly outperform advanced baselines in rating predictions and review generation tasks. For rating prediction tasks, it outperforms cross-domain and single-domain collaborative filtering as well as hybrid recommender systems. Furthermore, our review generation experiments suggest an improved perplexity score and transfer of reviewmore »information in DHCD.« less
  9. One of the essential problems, in educational data mining, is to predict students' performance on future learning materials, such as problems, assignments, and quizzes. Pioneer algorithms for predicting student performance mostly rely on two sources of information: students' past performance, and learning materials' domain knowledge model. The domain knowledge model, traditionally curated by domain experts maps learning materials to concepts, topics, or knowledge components that are presented in them. However, creating a domain model by manually labeling the learning material can be a difficult and time-consuming task. In this paper, we propose a tensor factorization model for student performance prediction that does not rely on a predefined domain model. Our proposed algorithm models student knowledge as a soft membership of latent concepts. It also represents the knowledge acquisition process with an added rank-based constraint in the tensor factorization objective function. Our experiments show that the proposed model outperforms state-of-the-art algorithms in predicting student performance in two real-world datasets, and is robust to hyper-parameters.