March 24: 11am–1pm Boston / 8–10am Oakland / 3–5pm London, virtual

Pre Workshop, March 23: 11am–12:30pm Boston / 8–9:30am Oakland / 3–4:30pm London, virtual

Please join us on 3/24 at 11am–1pm Boston / 8–10am Oakland / 3–5pm London, for the workshop "AI for Text Analysis with Python Using BERT and PyTorch."

This event is free and open to the public, but registration is required. RSVP here for the Zoom link for both the workshop and pre-workshop. 

AI allows humans to create a model that can act as an extension of the creator's mind and classify data based on predetermined categories. Manually tagging thousands of rows of data can often be cumbersome and time consuming. Forming a human-machine relationship to classify data can save researchers time and help catalyze data analysis and classification on projects that would otherwise take an untenable number of working hours.

This workshop will teach participants how to use Python with modern deep learning approaches for AI and text classification, creating a human-machine relationship to process and classify textual datasets. Learn how to use pre-trained BERT models and the Transformers library to understand and encode textual data. Use pandas, a Python library with extensive functionality for manipulating data, to clean and manipulate a dataframe (a table in pandas). Participants will also learn how to fine-tune BERT models and build neural network classification pipelines with PyTorch (a popular open source deep learning framework). Examples of projects that can be undertaken using these methods include sentiment analysis of social media posts, topic classification of historical newspaper archives, genre classification of literary texts, analysis of political discourse, identification of themes in survey responses, and classification of historical documents by time period or authorship.

There will be an optional virtual pre-workshop "Introduction to Python" 3/23 at 11am–12:30pm Boston / 8–9:30am Oakland / 3–4:30pm London. The pre-workshop covers the Python programming language tasks required to successfully participate in the text analysis workshop. Learners who are unfamiliar with how to use loc functions and python string methods to manipulate data and create new columns should plan to attend the pre-workshop, and all are welcome to attend.