Investigating Instructional Designers’ Expressed Needs during the Pandemic: A Follow-Up Study Using Natural Language Processing

The purpose of this follow-up study was to investigate further the expressed needs of Instructional Designers (IDers) from a large public Facebook group. Our previous original research (Abramenka-Lachheb et al., 2021a) reported that IDers expressed needs during the pandemic in several categories, including: (1) educational technology, (2) job-related, (3) announcement, (4) general pedagogical advice, and (5) COVID-related pedagogical advice. In this study, we implemented natural language processing (NLP), entity recognition, and topic modeling to extract hidden topic patterns in the reported categories in our previous research. We answered the following research questions: (RQ1) What are the most frequent words and word probabilities in each expressed need category? (RQ2) Which entities are prominent in each expressed need category? (RQ3) What latent topic structures exist in each expressed need category? The findings suggested expressed needs in educational technology tools, theories, ID consulting, and assessment and proctoring alternatives. The impact of our research documents the elements exchanged in the online environment during the COVID-19 pandemic.