EAGER: Social Media Participation as Indicator of Actors, Awareness, Attitudes, and Activities Related to STEM Education

点击翻译按钮获取中文摘要

A strong and productive STEM workforce is essential for the socio-economic well-being of the nation. Consequently, efforts to improve STEM education are undertaken each year across a range of federal and state agencies and they support thousands of STEM education events, activities, and initiatives. These efforts have been successful to some degree but participation by populations historically underrepresented in STEM continues to lag at a time when STEM workforce requirements are increasing. In order to improve future efforts, it is critical to build a nuanced and empirical understanding of the overall STEM space: What is the nature of issues related to STEM that garner interest? Who shows an interest and participates? What are the outcomes and impact of different STEM related initiatives? This proposed project will use social media data to study these issues and answer such questions. Social media data is an underutilized resource as almost 87% of the American population now participates in some form of social media activity. This project has the potential to improve and increase the impact of STEM education related efforts by illuminating ideas and activities of interest to people, current efforts in place, and what participants share and where. This information can be used for efforts such as broadening participation by better targeting campaigns intended to increase interest in STEM and by connecting individuals and organizations to create more momentum for an idea, event or topic.This study will use Twitter data and will focus on studying: (1) Actors - who participates in STEM education issues? (2) Awareness - what do participants know? (3) Attitudes - what attitude and beliefs do participants hold? (4) Activities - what do the participants do? what activities do they participate in? More specifically, the investigative team will use novel methodology to (a) analyze interaction patterns of the categorized users and create interaction networks by considering nodes as users and edges as the interaction strength; (b) use topic modeling techniques to gain insight about users' awareness of STEM; (c) employ target-specific sentiment mining techniques to gain insight about users' attitudes; (d) use geographic and spatio-temporal analysis, such as Density Based Spatial Clustering of Applications with Noise (DBSCAN), to gain insight about STEM activities. This project has the potential to contribute to our understanding of STEM education from the lens of social media. There is novelty in the approach and the methods of this project that serves to potentially transform how social media in STEM education is utilized.