This workshop will introduce participants to an automated approach to content analysis that combines machine learning and computational text analysis to replace/augment human encoding of qualitative data. We will use the nltk and scikit learn packages in Python to extract features from a sample dataset of companies’ annual reports. We will then use the extracted features to train an algorithm to predict the presence of latent meanings in a text like optimism and pessimism about the future.
This workshop will be offered as an online session via Zoom. You must register for this workshop to receive the Zoom link via a confirmation email. On the day of the workshop, use the link to join the session. Participants do not need a video camera or a microphone, but will need an audio connection to hear the instructor.
Contact Todd Schifeling at todd.schifeling@temple.edu with any questions.