Demonstrating Use of Natural Language Processing to Compare College of Engineering Mission Statements

Board 192: Identifying and addressing the barriers to advancement for women in the engineering professoriate: A systematic review of literature

“…Following an initial review of 191 titles, 48 papers passed our inclusion criteria, which we reviewed 31 post-exclusion of those with low quality. Figure 1 (adapted from [14]) details the steps in the review process, using the Search-Screen-Appraise method described in [10].…”

“…We find that such themes around isolation, lack of belonging or work-life balance, among others are parallel to those uncovered in prior research through studying engineering students' perceptions (e.g., [17] - [19]). Opportunities for future work include deeper dives into the interventions themselves and investigating whether these interventions to recruit and retain women in the professoriate vary by institution type (e.g., based on the mission and vision of the institution [20]). Echoing Smith's argument in Diversity's Promise for Higher Education [21], this research insists that if excellence is sought in diverse society (such as in increasingly diverse engineering academia), then diversity cannot be an afterthought.…”

Using Natural Language Processing to Facilitate Student Feedback Analysis

“…In engineering education, there have been limited applications of NLP on either the research or teaching side. The more modern applications have applied standard statistical and machine learning techniques such as rule-based classifiers for assessing student responses [19]- [21], college mission statements [22], writing exercises [23], and emotions in student stories of their transitions to university [24]. Unfortunately, these kinds of rule-based systems tend to be brittle and poorly handle variations in language to express the same concept.…”

Preparing Engineering Students to Find the Best Job Fit: Starting Early with the Career Development Process

“…To ensure the quality of our analysis, we used a combination of expert review of the code definitions and interrater reliability checks [30]. During the process, the analyst provided the interrater (an analyst on the larger [e.g., 31, 32] project) with a set of codes and definitions, and the definitions were discussed for clarity. Next, a random sampling of transcript data was provided to the intercoder who coded them.…”