Text Mining Undergraduate Engineering Programs' Applications: the Role of Gender, Nationality, and Socio-economic Status

Abstract

Authors are encouraged to submit new papers to INFORMS journals by means of a style file template, which includes the journal title. However, use of a template does not certify that the paper has been accepted for publication in the named journal. INFORMS journal templates are for the exclusive purpose of submitting to an INFORMS journal and should not be used to distribute the papers in print or online or to submit the papers to another publication.

Communication patterns in engineering enterprise social networks: an exploratory analysis using short text topic modelling

“…We wanted to explore the ability of topic modelling to find expected patterns of convergence and divergence of engineering design teams; thus, we built a topic model for each team-phase, using identical hyperparameters, and compared how these models changed throughout the design process. We used topic modelling as an exploratory, unsupervised learning method, to discover the underlying clustering of messages within each team, which is a common use of topic modelling in past work (Uys, Du Preez & Uys 2008;Lin & He 2009;Snider et al 2017;Naseem et al 2020;Park et al 2020;Lin, Ghaddar & Hurst 2021;Shekhar et al 2021). This means that we do not have true labels for the topic of each message, which would be near impossible to obtain given the volume of our data.…”

“…A single topic model trained on all teams would require a huge number of topics and would likely combine all project-specific technical terms into the same topics as they are used less frequently than planning or project management terms. Topics can be very product-specific, so we extracted topics on a case-by-case basis, similar to what has been previously done (Snider Lin et al 2021). Additionally, building individual models for each team and phase allowed us to explore the number and coherence of topics by phase as an estimation of convergence and divergence in the design process.…”

Artificial Intelligence in Educational Research

“…In the study titled "Text Mining Undergraduate Engineering Programs' Applications: The Role of Gender, Nationality, and Socio-economic Status" [13], the aim was to identify user behavior patterns related to Massive Open Online Courses (MOOCs). For this purpose, topic models with Latent Dirichlet allocation were employed.…”