MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs

Yu, Jifan; Luo, Gan; Xiao, Tong; Zhong, Qingyang; Wang, Yuquan; Feng, Wenzheng; Luo, Junyi; Wang, Chenyu; Hou, Lei; Li, Juanzi; Liu, Zhiyuan; Tang, Jie

doi:10.18653/v1/2020.acl-main.285

Cited by 97 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the concept graph is not able to cover different domains. Beyond the document recommendation, some data inherently appears with the prerequisite relationships, like lecture data created in the MOOCs [40,41], as different lectures credited by the same student are time-variant. This notorious problem can be automatically sidestepped by leveraging citation relationship as we did.…”

Section: Related Workmentioning

confidence: 99%

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

Ding¹,

Xiang²,

Ou³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent years have witnessed the dramatic growth of paper volumes with plenty of new research papers published every day, especially in the area of computer science. How to glean papers worth reading from the massive literature to do a quick survey or keep up with the latest advancement about a specific research topic has become a challenging task. Existing academic search engines such as Google Scholar return relevant papers by individually calculating the relevance between each paper and query. However, such systems usually omit the prerequisite chains of a research topic and cannot form a meaningful reading path. In this paper, we introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query. To serve as a research benchmark, we further propose Sur-veyBank, a dataset consisting of large quantities of survey papers in the field of computer science as well as their citation relationships. Each survey paper contains key phrases extracted from its title and multi-level reading lists inferred from its references. Furthermore, we propose a graph-optimization-based approach for reading path generation which takes the relationship between papers into account. Extensive evaluations demonstrate that our approach outperforms other baselines. A Real-time Reading Path Generation (RePaGer) system has been also implemented with our designed model. To the best of our knowledge, we are the first to target this important research problem. Our source code of RePaGer system and SurveyBank dataset can be found here.

show abstract

Section: Related Workmentioning

confidence: 99%

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

Ding¹,

Xiang²,

Ou³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…They include mathematics ASSISTments 1 [32,55], problem solving interactions [18], or multiple choice questions 2 [56,57]), all of which are noteworthy although they do not focus on implicit feedback and engagement. MOOCCube is a very recently released dataset that contains a spectrum of different statistics relating to learner-MOOC interactions including implicit and explicit test taking activity [62]. Although this dataset may contain data that can be used to predict learner engagement with implicit feedback, the dataset has only been used in prerequisite detection task which is very different.…”

Section: Related Datasetsmentioning

confidence: 99%

“…Developing artificial intelligence systems that, mildly at least, understand the structure of knowledge is foundational to building effective recommendation systems for lifelong education [13,41,62], as well as for many other applications related to knowledge management and tracing [35,61]. In the context of personalised education, the research communities have tirelessly worked on building Intelligent Tutoring Systems (ITS) which have been their focus from the early applications of AI in education [19].…”

Section: Introductionmentioning

confidence: 99%

PEEK: A Large Dataset of Learner Engagement with Educational Videos

Bulathwela,

Perez-Ortiz,

Novak

et al. 2021

Preprint

View full text Add to dashboard Cite

In this work, we release a large and novel dataset of learners engaging with educational videos in-the-wild. The dataset, named Personalised Educational Engagement with Knowledge Topics (PEEK), is one of the first publicly available datasets that address personalised educational engagement. Educational recommenders have received much less attention in comparison to e-commerce and entertainment-related recommenders, even though efficient personalised learning systems could improve learning gains significantly. One of the main challenges in advancing this research direction is the scarcity of large, publicly available datasets. In the PEEK dataset, educational video lectures have been associated with Wikipedia concepts related to the material of the lecture, thus providing a humanly intuitive taxonomy. We believe that granular learner engagement signals, in unison with rich content representations, will pave the way to building powerful personalisation algorithms that will revolutionise educational and informational recommendation systems. Towards this goal, we 1) construct a novel dataset from a popular video lecture repository, 2) identify a set of benchmark algorithms to model engagement, and 3) run extensive experimentation on the PEEK dataset to demonstrate its value. Our experiments with the dataset show promise in building powerful informational recommender systems. The dataset and the support code is available at https://github.com/sahanbull/PEEK-Dataset.

show abstract

“…With the rapid growth of online educational resources in diverse fields, people need an efficient way to acquire new knowledge. Building a concept graph can help people design a correct and efficient study path (ALSaad et al, 2018;Yu et al, 2020). There are mainly two approaches to learning prerequisite relations between concepts: one is to extract the relations directly from course content, video sequences, textbooks, or Wikipedia articles (Yang et al, 2015b;Pan et al, 2017;Alzetta et al, 2019), but this approach requires extra work on feature engineering and keyword extraction.…”

Section: Introductionmentioning

confidence: 99%

“…Existing methods formulate this question as a classification task. A typical method is to encode concept pairs and train a classifier to predict if there is a prerequisite relation (Alzetta et al, 2019;Yu et al, 2020). However, this method requires annotated prerequisite pairs during training.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders

Li¹,

Yan²,

Li³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Learning prerequisite chains is an essential task for efficiently acquiring knowledge in both known and unknown domains. For example, one may be an expert in the natural language processing (NLP) domain but want to determine the best order to learn new concepts in an unfamiliar Computer Vision domain (CV). Both domains share some common concepts, such as machine learning basics and deep learning models. In this paper, we propose unsupervised cross-domain concept prerequisite chain learning using an optimized variational graph autoencoder. Our model learns to transfer concept prerequisite relations from an information-rich domain (source domain) to an information-poor domain (target domain), substantially surpassing other baseline models. Also, we expand an existing dataset by introducing two new domains--CV and Bioinformatics (BIO). The annotated data and resources, as well as the code, will be made publicly available.

show abstract

MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs

Cited by 97 publications

References 17 publications

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

PEEK: A Large Dataset of Learner Engagement with Educational Videos

Unsupervised Cross-Domain Prerequisite Chain Learning using Variational Graph Autoencoders

Contact Info

Product

Resources

About