Fall Semester: Reducing Drug-Related Harms Using Internet-Based “Big Data”: Machine Learning and AI Methods
BSHES 740 Class Nbr 5626
This course will prepare students to conduct ethical, rigorous, and theoretically-informed analyses of “big data” (machine learning/social media) in the context of research and interventions into intersecting crises of substance use disorders (SUDs) and drug-related harms.
Syllabus Example: TADA_Syllabus Example Fall
Pre-Requisites:
It is recommended that students be comfortable working in a Unix/Linux environment, in addition to being familiar with database formatting using R or SQL via SAS.
Prior completion of the following courses/ equivalents is also needed to successfully complete this module:
- Regression (e.g.BIOS 501, BSHES 700),
- At least one statistical programming course, such as SAS (e.g.BIOS 501) or R (e.g.BIOS 544)
Spring Semester: Reducing Drug-Related Harms Using “Big Data”: Administrative, Geospatial & Network Sources
BSHES 735 Class Nbr 5214
This course will prepare students to conduct ethical, rigorous, and theoretically–informed analyses of three types of “big data” (administrative, geospatial, and social network data) in the context of research and interventions into intersecting crises of substance use disorders (SUDs) and drug–related harms.
It will apply the strengths of social and behavioral sciences – including a focus on theory and validity – to the emerging field of advanced data analytics.
Syllabus Example: TADA_Syllabus_Example_Spring*
Pre-Requisites:
This course will require computing in different programs and different environments. Familiarity and comfort with the following is needed to successfully complete the course:
• Regression (examples: BIOS 501, BSHES 700)
• SAS (examples: BIOS 501)
• R (examples: BIOS 544)
We recommend, but do not require, taking the Spring course first.
*Syllabi examples are for course planning purposes only and are subject to change.