owentemple / TED-talks
A natural language processing project to reveal linguistic features that predict a persuasive TED Talk. I webscraped every TED Talk transcript and it's metadata through 2017 and then used decision trees, random forest regressors, and linear regression to find key predictors of persuasive ratings by viewers.
☆19Updated 6 years ago
Related projects: ⓘ
- Promoting Positive Climate Change Conversations via Twitter☆14Updated 6 years ago
- Extracting data from Twitter for #machinelearningflashcards☆41Updated 2 years ago
- Repository containing script on how I processed and charted Yelp data.☆29Updated 9 years ago
- ☆20Updated 8 years ago
- Topic models (just LDA for now) on the Hacker News corpus☆22Updated 9 years ago
- ☆11Updated 8 years ago
- An open-source implementation of the Linguistic Inquiry Word Count in Python☆15Updated 7 years ago
- Speech recognition using Google Cloud Speech API☆25Updated 7 years ago
- An analysis of the sentiments of tweets using the Twitter API for my data science class☆13Updated 11 years ago
- Tutorials for web scraping and crawling☆11Updated 4 years ago
- Data and code supporting BuzzFeed News' evaluation of forecasters' predictions for the November 2016 U.S. presidential and Senate electio…☆22Updated 7 years ago
- An experiment of using the LDA machine learning algorithm to generate topics from documents and tag them with those topics☆17Updated 7 years ago
- Analysis of public dataset about bicycle trips under Bay Area Bike Share program☆24Updated 7 years ago
- ☆32Updated 10 months ago
- Experiments on english wikipedia. GloVe and word2vec.☆13Updated 8 years ago
- Tweets from the third presidential debate in 2016☆18Updated 7 years ago
- ☆14Updated 6 years ago
- Code examples and data for the KiwiPyCon 2014 NLP tutorial☆40Updated 10 years ago
- Project files related to topic modeling of NYT articles regarding mental health☆17Updated 6 years ago
- Code used to compare sentiments of various sermons☆24Updated 12 years ago
- Seers Accuracy competition on Analytics Vidhya☆11Updated 8 years ago
- Build intelligent data-driven applications with minimal effort. Sentence Clustering, Topics Extraction, Text Similarity, Opinion Summariz…☆40Updated 4 years ago
- Because you're computing conversion rates wrong☆16Updated 7 years ago
- ☆46Updated 5 months ago
- Webscikit is a set of tools to run a webserver as a JSON Webservice for scikit-learn predictions. It comes with two examples: boston and …☆9Updated 6 years ago
- A processing pipeline for JSON-formatted Tweet data, such as that returned by Twitter APIs.☆11Updated 6 years ago
- Source code for the Twitter Hybrid Sentiment Classifier used in Semeval 2014 competition. (Sentiment Analysis system)☆13Updated 10 years ago
- This is the text partitioner project for Python.☆20Updated 5 years ago
- UMD Course on Computational Journalism☆25Updated 7 years ago
- Twitter user classification tutorial at PyCon France 2016☆21Updated last year