Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Predicting peer group effects on University exam results

Scanlon, Philip and Smeaton, Alan F. orcid logoORCID: 0000-0003-1028-8389 (2015) Predicting peer group effects on University exam results. In: EventInsight Student Conference (INSIGHT-SC 2015), 30 Oct 2015, NUIG, Galway, Ireland.

Abstract
There has been a multitude of studies and research papers in the areas of the influence on an individual, of the heterogeneous groups to which they become members. Manski [1] addresses the concept of “Reflection” (influence) within the group dynamic. His research found that inference of influence is only possible if additional information about the subjects making up the group is known. Using anonymised campus wifi access logs collected by the Eduroam system it is the intention of this research to identify interaction of students and thus identify group members. Once a group’s members have been identified additional academic, social and environmental information will be used to identify students whose academic studies could benefit from early stage intervention.
Metadata
Item Type:Conference or Workshop Item (Poster)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Machine learning
Social Sciences > Educational technology
Computer Science > Information retrieval
DCU Faculties and Centres:Research Institutes and Centres > INSIGHT Centre for Data Analytics
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:This project has been funded by Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289
ID Code:21212
Deposited On:11 May 2016 10:23 by Philip Scanlon . Last Modified 31 Oct 2018 11:46
Documents

Full text available as:

[thumbnail of poster_wifi_logs.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
2MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record