skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Fine-Tuning Large Language Models for Data Augmentation to Detect At-Risk Students in Online Learning Communities
We introduce a working approach that combines the method of fine-tuning large language models (LLMs) to create augmented data for the regression predictive models aimed at detecting at-risk students in online learning communities. This approach has the potential to leverage scarce data to improve urgency detection, and it can also present the role of artificial intelligence in enhancing the resilience of educational communities and ensuring timely interventions within online learning settings.  more » « less
Award ID(s):
2331379
PAR ID:
10531983
Author(s) / Creator(s):
;
Publisher / Repository:
International Society of the Learning Sciences
Date Published:
Page Range / eLocation ID:
441 to 442
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Interactive learning environments)
    Participating in online communities has significant benefits to students learning in terms of students’ motivation, persistence, and learning outcomes. However, maintaining and supporting online learning communities is very challenging and requires tremendous work. Automatic support is desirable in this situation. The purpose of this work is to explore the use of deep learning algorithms for automatic text generation in providing emotional and community support for a massive online learning community, Scratch. Particularly, state-of-art deep learning language models GPT-2 and recurrent neural network (RNN) are trained using two million comments from the online learning community. We then conduct both a readability test and human evaluation on the automatically generated results for offering support to the online students. The results show that the GPT-2 language model can provide timely and human-written like replies in a style genuine to the data set and context for offering related support. 
    more » « less
  2. ; ; ; (, 2021 ASEE Virtual Annual Conference Content Access)
    This NSF-IUSE exploration and design project began in fall 2018 and features cross-disciplinary collaboration between engineering, math, and psychology faculty to develop learning activities with 3D-printed models, build the theoretical basis for how they support learning, and assess their effectiveness in the classroom. We are exploring how such models can scaffold spatial skills and support learners’ development of conceptual understanding and representational competence in calculus and engineering statics. We are also exploring how to leverage the model-based activities to embed spatial skills training into these courses. The project’s original focus was on group learning in classroom activities with shared manipulatives. After a year of development and pilot activities, we commenced data collection in classroom implementations of a relatively mature curriculum starting fall 2019. Data collection ended abruptly in March 2020 when we had to shift gears in the context of a shift to online learning amid the COVID-19 pandemic. With uncertainty as to when the use of shared hands-on models in a collaborative in-person learning context would be feasible again, it was clear a change in approach would be necessary. We have since developed new versions of the models and associated curriculum designed for independent at-home use in the context of online learning. We implemented the new curricula in an online statics courses in fall 2020 and in multiple sections of online calculus courses in winter 2021. In this paper, we describe our strategies for implementing hands-on learning at home. We also present some example activities and compare the approach to the face-to-face versions. Finally, we compare student feedback results on the online activities to analogous feedback data from the classroom implementations and discuss implications for the anticipated return to face-to-face learning in the classroom. 
    more » « less
  3. ; ; ; (, ASEE Annual Conference proceedings)
    null (Ed.)
    This NSF-IUSE exploration and design project began in fall 2018 and features cross-disciplinary collaboration between engineering, math, and psychology faculty to develop learning activities with 3D-printed models, build the theoretical basis for how they support learning, and assess their effectiveness in the classroom. We are exploring how such models can scaffold spatial skills and support learners’ development of conceptual understanding and representational competence in calculus and engineering statics. We are also exploring how to leverage the model-based activities to embed spatial skills training into these courses. The project’s original focus was on group learning in classroom activities with shared manipulatives. After a year of development and pilot activities, we commenced data collection in classroom implementations of a relatively mature curriculum starting fall 2019. Data collection ended abruptly in March 2020 when we had to shift gears in the context of a shift to online learning amid the COVID-19 pandemic. With uncertainty as to when the use of shared hands-on models in a collaborative in-person learning context would be feasible again, it was clear a change in approach would be necessary. We have since developed new versions of the models and associated curriculum designed for independent at-home use in the context of online learning. We implemented the new curricula in an online statics courses in fall 2020 and in multiple sections of online calculus courses in winter 2021. In this paper, we describe our strategies for implementing hands-on learning at home. We also present some example activities and compare the approach to the face-to-face versions. Finally, we compare student feedback results on the online activities to analogous feedback data from the classroom implementations and discuss implications for the anticipated return to face-to-face learning in the classroom. 
    more » « less
  4. ; ; ; ; (, ASEE annual conference)
    Over the past decade, practices related to online learning have become increasingly varied and legitimated. Whether it be formal e-learning in K-12 or at colleges and universities or casual perusing of the internet, many people have found communities online to support their own endeavors. Recently, due to the Covid-19 pandemic most colleges and universities have been forced to shift partly or entirely to remote learning due to campus closures. Further, even in cases in which a campus is open, many universities have limited access to their makerspace due to social distancing and capacity requirements. In response, this Work in Progress study investigates how online making communities and resources are supporting student learning through making. Through in-depth phenomenologically-based interviews conducted both before and during the pandemic, this study offers rich insights into how students are learning from and engaging in online maker communities/resources as a central part of their development as a maker. Through qualitative data analysis, we develop a model for how students are learning online. These findings show the role digital spaces play in developing competent, inspired makers. 
    more » « less
  5. ; (, Annual review of statistics and its application)
    null (Ed.)
    Online learning is a framework for the design and analysis of algorithms that build predictive models by processing data one at the time. Besides being computationally efficient, online algorithms enjoy theoretical performance guarantees that do not rely on statistical assumptions on the data source. In this survey, we describe some of the most important algorithmic ideas behind online learning and explain the main mathematical tools for their analysis. Our reference framework is online convex optimization, a sequential version of convex optimization within which most online algorithms are formulated. More specifically, we provide an in-depth description of Online Mirror Descent and Follow the Regularized Leader, two of the most fundamental algorithms in online learning. As the tuning of parameters is a typically difficult task in sequential data analysis, in the last part of the survey we focus on coin-betting, an information-theoretic approach to the design of parameter-free online algorithms with good theoretical guarantees. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email