The main objective of Personalized Tour Recommendation (PTR) is to generate a sequence of point-of-interest (POIs) for a particular tourist, according to the user-specific constraints such as duration time, start and end points, the number of attractions planned to visit, and so on. Previous PTR solutions are based on either heuristics for solving the orienteering problem to maximize a global reward with a specified budget or approaches attempting to learn user visiting preferences and transition patterns with the stochastic process or recurrent neural networks. However, existing learning methodologies rely on historical trips to train the model and use the next visited POI as the supervised signal, which may not fully capture the coherence of preferences and thus recommend similar trips to different users, primarily due to the data sparsity problem and long-tailed distribution of POI popularity. This work presents a novel tour recommendation model by distilling knowledge and supervision signals from the trips in a self-supervised manner. We propose Contrastive Trajectory Learning for Tour Recommendation (CTLTR), which utilizes the intrinsic POI dependencies and traveling intent to discover extra knowledge and augments the sparse data via pre-training auxiliary self-supervised objectives. CTLTR provides a principled way to characterize the inherent data correlations while tackling the implicit feedback and weak supervision problems by learning robust representations applicable for tour planning. We introduce a hierarchical recurrent encoder-decoder to identify tourists’ intentions and use the contrastive loss to discover subsequence semantics and their sequential patterns through maximizing the mutual information. Additionally, we observe that a data augmentation step as the preliminary of contrastive learning can solve the overfitting issue resulting from data sparsity. We conduct extensive experiments on a range of real-world datasets and demonstrate that our model can significantly improve the recommendation performance over the state-of-the-art baselines in terms of both recommendation accuracy and visiting orders.
more »
« less
Proximity-based educational recommendations: A multi-objective framework
Personalized learning and educational recommender systems are integral parts of modern online education systems. In this context, the problem of recommending the best learning material to students is a perfect example of sequential multi-objective recommendation. Learning material recommenders need to optimize for and balance between multiple goals, such as adapting to student ability, adjusting the learning material difficulty, increasing student knowledge, and serving student interest, at every step of the student learning sequence. However, the obscurity and incompatibility of these objectives pose additional challenges for learning material recommenders. To address these challenges, we propose Proximity-based Educational Recommendation (PEAR), a recommendation framework that suggests a ranked list of problems by approximating and balancing between problem difficulty and student ability. To achieve an accurate approximation of these objectives, PEAR can integrate with any state-of-the-art student and domain knowledge model. As an example of such student and domain knowledge model, we introduce Deep Q-matrix based Knowledge Tracing model (DQKT), and integrate PEAR with it. Rather than static recommendations, this framework dynamically suggests new problems at each step by tracking student knowledge level over time. We use an offline evaluation framework, Robust Evaluation Matrix (REM), to compare PEAR with various baseline recommendation policies under three different student simulators and demonstrate the effectiveness of our proposed model. We experiment with different student trajectory lengths and show that while PEAR can perform better than the baseline policies with fewer data, it is also robust with longer sequence lengths.
more »
« less
- Award ID(s):
- 2047500
- NSF-PAR ID:
- 10434440
- Date Published:
- Journal Name:
- The 2nd Workshop on Multi-Objective Recommender Systems (MORS’22)
- Page Range / eLocation ID:
- 1-17
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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.more » « less
-
This NSF Grantees poster discusses an early phase Revolutionizing Engineering Departments (RED) project which is designed to address preparing engineering students to address large scale societal problems, the solutions of which integrate multiple disciplinary perspectives. These types of problems are often termed “convergent problems”. The idea of convergence captures how different domains of expertise contribute to solving a problem, but also the value of the network of connections between areas of knowledge that is built in undertaking such activities. While most existing efforts at convergence focus at the graduate and post-graduate levels, this project supports student development of capabilities to address convergent problems in an undergraduate disciplinary-based degree program in electrical and computer engineering. This poster discusses some of the challenges faced in implementing such learning including how to decouple engineering topics from societal concerns in ways that are relevant to undergraduate students yet retain aspects of convergence, negotiations between faculty on ways to balance discipline-specific skills with the breadth required for systemic understanding, and challenges in integrating relevant projects into courses with different faculty and instructional learning goals. One of the features of the project is that it builds on ideas from Communities of Transformation by basing activities on a coherent philosophical model that guides theories of change. The project has adopted Amartya Sen’s Development as Freedom or capabilities framework as the organizing philosophy. In this model the freedom for individuals to develop capabilities they value is viewed as both the means and end of development. The overarching goal of the project is then for students to build personalized frameworks based on their value systems which allow them to later address complex, convergent problems. Framework development by individual students is supported in the project through several activities: modifying grading practices to provide detailed feedback on skills that support convergence, eliciting self-narratives from students about their pathways through courses and projects with the goal of developing reflection, and carefully integrating educational software solutions that can reduce some aspects of faculty workload which is hypothesized to enable faculty to focus efforts on integrating convergent projects throughout the curriculum. The poster will present initial results on the interventions to the program including grading, software integration, projects, and narratives. The work presented will also cover an ethnographic study of faculty practices which serves as an early-stage baseline to calibrate longer-term changes.more » « less
-
This Research Full paper focuses on perceptions and experiences of freshman and sophomore engineering students when playing an online serious engineering game that was designed to improve engineering intuition and knowledge of statics. Use of serious educational engineering games has increased in engineering education to help students increase technical competencies in engineering disciplines. However, few have investigated how these engineering games are experienced by the students; how games influence students' perceptions of learning, or how these factors may lead to inequitable perspectives among diverse populations of students. Purpose/Hypothesis: The purpose of this study was to explore the perceptions, appeal, and opinions about the efficacy of educational online games among a diverse population of students in an engineering mechanics statics course. It was hypothesized that compared to majority groups (e.g., men, White), women of color who are engineering students would experience less connections to the online educational game in terms of ease of use and level of frustration while playing. It is believed that these discordant views may negatively influence the game's appeal and efficacy towards learning engineering in this population of students. Design/Method: The Technology Acceptance Model (TAM) is expanded in this study, where the perspectives of women of colour (Latinx, Asian and African American) engineering students are explored. The research approach employed in this study is a mixed-method sequential exploratory design, where students first played the online engineering educational game, then completed a questionnaire, followed by participation in a focus group. Responses were initially analyzed through open and magnitude coding approaches to understand whether students thought these educational games reflected their personal culture. Results: Preliminary results indicate that though the majority of the students were receptive to using the online engineering software for their engineering education, merely a few intimated that they would use this software for engineering exam or technical job interview preparation. A level-one categorical analysis identified a few themes that comprised unintended preservation of inequality in favor of students who enjoyed contest-based education and game technology. Competition-based valuation of presumed mastery of course content fostered anxiety and intimidation among students, which caused some to "game the game" instead of studying the material, to meet grade goals. Some students indicated that they spent more time (than necessary) to learn the goals of the game than engineering content itself, suggesting a need to better integrate course material while minimizing cognitive effort in learning to navigate the game. Conclusions: Preliminary results indicate that engineering software's design and the way is coupled with course grading and assessment of learning outcomes, affect student perceptions of the technology's acceptance, usefulness, and ease of use as a "learning tool." Students were found to have different expectations of serious games juxtaposed software/apps designed for entertainment. Conclusions also indicate that acceptance of inquiry-based educational games in a classroom among diverse populations of students should clearly articulate and connect the game goals/objectives with class curriculum content. Findings also indicate that a multifaceted schema of tools, such as feedback on game challenges, and explanations for predictions of the game should be included in game/app designs.more » « less
-
Agrawal, Garima (Ed.)Cybersecurity education is exceptionally challenging as it involves learning the complex attacks; tools and developing critical problem-solving skills to defend the systems. For a student or novice researcher in the cybersecurity domain, there is a need to design an adaptive learning strategy that can break complex tasks and concepts into simple representations. An AI-enabled automated cybersecurity education system can improve cognitive engagement and active learning. Knowledge graphs (KG) provide a visual representation in a graph that can reason and interpret from the underlying data, making them suitable for use in education and interactive learning. However, there are no publicly available datasets for the cybersecurity education domain to build such systems. The data is present as unstructured educational course material, Wiki pages, capture the flag (CTF) writeups, etc. Creating knowledge graphs from unstructured text is challenging without an ontology or annotated dataset. However, data annotation for cybersecurity needs domain experts. To address these gaps, we made three contributions in this paper. First, we propose an ontology for the cybersecurity education domain for students and novice learners. Second, we develop AISecKG, a triple dataset with cybersecurity-related entities and relations as defined by the ontology. This dataset can be used to construct knowledge graphs to teach cybersecurity and promote cognitive learning. It can also be used to build downstream applications like recommendation systems or self-learning question-answering systems for students. The dataset would also help identify malicious named entities and their probable impact. Third, using this dataset, we show a downstream application to extract custom-named entities from texts and educational material on cybersecurity.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
