Connectionist recommendation in the wild: on the utility and scrutability of neural networks for personalized course guidance

Pardos, Zachary A.; Zhai, Fan; Jiang, Weijie

doi:10.1007/s11257-019-09218-7

Cited by 50 publications

(27 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of responding to early signs of trouble in a class, they instead aim to help students select their courses. An example of a deployed system is AskOski at University of California, Berkeley, which uses historic enrollments and machine learning to suggest courses across campus that may be relevant to students’ interests and links them to the campus degree audit system to give personalized recommendations of courses that would satisfy students’ unmet graduation requirement (Pardos, Fan, et al, 2019). Another deployed system, Stanford’s CARTA system, surfaces historic course grade distributions, course evaluations, and common courses taken before and after a course (Chaturapruek et al, 2018).…”

Section: Macrolevel Big Datamentioning

confidence: 99%

Mining Big Data in Education: Affordances and Challenges

Fischer

Pardos

Baker

et al. 2020

Review of Research in Education

Self Cite

252

138

View full text Add to dashboard Cite

The emergence of big data in educational contexts has led to new data-driven approaches to support informed decision making and efforts to improve educational effectiveness. Digital traces of student behavior promise more scalable and finer-grained understanding and support of learning processes, which were previously too costly to obtain with traditional data sources and methodologies. This synthetic review describes the affordances and applications of microlevel (e.g., clickstream data), mesolevel (e.g., text data), and macrolevel (e.g., institutional data) big data. For instance, clickstream data are often used to operationalize and understand knowledge, cognitive strategies, and behavioral processes in order to personalize and enhance instruction and learning. Corpora of student writing are often analyzed with natural language processing techniques to relate linguistic features to cognitive, social, behavioral, and affective processes. Institutional data are often used to improve student and administrational decision making through course guidance systems and early-warning systems. Furthermore, this chapter outlines current challenges of accessing, analyzing, and using big data. Such challenges include balancing data privacy and protection with data sharing and research, training researchers in educational data science methodologies, and navigating the tensions between explanation and prediction. We argue that addressing these challenges is worthwhile given the potential benefits of mining big data in education.

show abstract

Section: Macrolevel Big Datamentioning

confidence: 99%

Mining Big Data in Education: Affordances and Challenges

Fischer

Pardos

Baker

et al. 2020

Review of Research in Education

Self Cite

252

138

View full text Add to dashboard Cite

show abstract

“…The paper Connectionist Recommendation in the Wild: On the utility, scrutability, and scalability of neural networks for personalized course guidance (Pardos et al 2019) is an example of a work that relies on embeddings to encode metadata. The authors propose Course2Vec, an adaptation of Word2Vec, to build a vector space representation of university courses.…”

Section: Papers In This Issuementioning

confidence: 99%

Trends in content-based recommendation

Lops

Jannach

Musto

et al. 2019

User Model User-Adap Inter

142

View full text Add to dashboard Cite

show abstract

“…Since this work began [59], the course vector representations have been integrated into a campus course recommendation system [17], allowing students to explore courses with conceptual overlap with a favorite course of theirs [60]. The semantic mapping technique has been used to augment course catalog descriptions with searchable inferred course topics [61], and translation between two institutions' course vector spaces has been shown to be capable of surfacing academically equivalent courses to expand transfer student pathways, a processes known as course articulation [62].…”

Section: Discussionmentioning

confidence: 99%

“…Our work relates to the field of learning analytics, where historical enrollment data have been used to predict the next courses a student will take [ 17 , 18 ], the grade they may receive in those courses [ 19 – 21 ], and the prerequisites that may prepare them to achieve their goals [ 20 , 22 ]. We contribute methods for learning the underlying semantics of curricular resources from data, a phase outlined in an early learning analytics vision document [ 23 ] as coming after predictive modeling and preceding adaptive course sequencing.…”

Section: Introductionmentioning

confidence: 99%

A university map of course knowledge

Pardos

Nam

2020

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Knowledge representation has gained in relevance as data from the ubiquitous digitization of behaviors amass and academia and industry seek methods to understand and reason about the information they encode. Success in this pursuit has emerged with data from natural language, where skip-grams and other linear connectionist models of distributed representation have surfaced scrutable relational structures which have also served as artifacts of anthropological interest. Natural language is, however, only a fraction of the big data deluge. Here we show that latent semantic structure can be informed by behavioral data and that domain knowledge can be extracted from this structure through visualization and a novel mapping of the text descriptions of elements onto this behaviorally informed representation. In this study, we use the course enrollment histories of 124,000 students at a public university to learn vector representations of its courses. From these course selection informed representations, a notable 88% of course attribute information was recovered, as well as 40% of course relationships constructed from prior domain knowledge and evaluated by analogy (e.g., Math 1B is to Honors Math 1B as Physics 7B is to Honors Physics 7B). To aid in interpretation of the learned structure, we create a semantic interpolation, translating course vectors to a bag-of-words of their respective catalog descriptions via regression. We find that representations learned from enrollment histories resolved courses to a level of semantic fidelity exceeding that of their catalog descriptions, revealing nuanced content differences between similar courses, as well as accurately describing departments the dataset had no course descriptions for. We end with a discussion of the possible mechanisms by which this semantic structure may be informed and implications for the nascent research and practice of data science.

show abstract

Connectionist recommendation in the wild: on the utility and scrutability of neural networks for personalized course guidance

Cited by 50 publications

References 66 publications

Mining Big Data in Education: Affordances and Challenges

Mining Big Data in Education: Affordances and Challenges

Trends in content-based recommendation

A university map of course knowledge

Contact Info

Product

Resources

About