Natural language processing with Python

ABOUT TALK
Our speaker, Chrissy Roig, will present about her Tweet Classification project in which she pulled tweets using Tweepy from the Twitter API. She will walk us through various methods she used to clean and classify the unlabeled data including wordninja, lemmatization and stopword removal, NLTK, KMeans clustering, wordcloud, TF-IDF, Doc2Vec and Word2Vec, PCA, and TSNE clustering, as well as transformers including RoBERTa and BERTopic. She will then show us how to visualize two methods of classification: labelling the text with the first hashtag present if one exists and using a dataset of pre-labelled news headlines to create a model that predicts tweet topic based on news headline and several clustering methods.

ABOUT SPEAKER
Chrissy Roig, a Chicago native, studied biology in undergrad. In 2018, two years after moving to Southwest Florida, she started learning computer programming, primarily with Python. After a semester in the FGCU software engineering program, she decided her heart was in data science. Chrissy is due to graduate from the Northwestern University Master’s program in Data Science with a specialization in Artificial Intelligence in December 2021.

This is a hybrid event (our first!).
For VIRTUAL attendance, please register here:
https://us02web.zoom.us/meeting/register/tZEtdO2tqDsrHtK-fn_VVtZdp1fWu3OU2VY9.
Once registered, you will receive a confirmation email containing information about joining the meeting.

For IN-PERSON attendance, join us at Fort Myers Regional Library (1651 Lee Street Fort Myers, FL 33901). We will be meeting at Rooms A-B located across from the main library building to the right of the playground (if you are coming from First St.) You can also enter from either side of Lee and Second Street, where you will find free parking.

To assure safety of all attendees, the COVID-19 safety protocols will be enforced. If you have any questions or concerns about attending this event in-person, please don’t hesitate to contact the organizers (Inessa Pawson and Zarela Graves).

AGENDA:
6:00 - Arrival /Networking
6:15 - Introduction and announcements by the organizers
6:30 - Natural Language Processing with Python, presented by Chrissy Roig
7:30 - Wrap Up
8:00 - After-party celebration at Patio de Leon (courtyard behind Downtown Pizza)

This event is co-hosted with our friends from SWFL Coders.