Deep Into the Tweet

on YouTube ↗19m

" summary

Detailed how-to for harvesting and parsing Twitter data with tweepy and Python, extracting JSON fields (full_text, ids, timestamps, user metadata, hashtags, URLs, emojis) and turning them into tables, maps and interaction graphs for social network analysis and sentiment or persuasion classification. Covers emoji handling with demoji and mentions deepmoji as an option. Notes API rate limits (roughly ~4,000 tweets per 15 minutes), encoding pitfalls, and provides runnable notebooks on GitHub whose code the uploader verifies still works.

AI-written summary · about

" chapters (11)

1. 0:00Twitter data mining intro
2. 1:33Twitter API credentials
3. 3:21Collecting tweets with Twitty
4. 5:27Tweet structure and metadata
5. 8:38Cleaning tweet text
6. 10:27User data and encoding
7. 11:29Working with emojis
8. 13:42Visualizing tweet data
9. 14:46Social network connections
10. 15:29Sentiment analysis on tweets
11. 16:35Q&A

" related talks

• 01h 05mSocial Text, Sentiment, and Tone AnalysisRuben Pertusa Lopez · PASS Business Analytics Conference 2013
• 30mAnalysing a TwitterBot using TextBlob, NLTK and PythonLachlan Blackhall · PyCon AU 2017
• 39mThe art and science of making computers understand sentiment and emotionPushpak Bhattacharyya · Anthill Inside 2018
• 42mWeaponizing Data Science for Social Engineering: Automated E2E Spear Phishing on TwitterJohn Seymour, Philip Tully · Black Hat USA 2016
• 40mPuppies or MuffinsSara Robinson · DevFest MN 2017
• 01h 26mData Driven Action: a primer on Data ScienceSarah Aerni, Srivatsan Ramanujam, Jarrod Vawdrey · SpringOne2GX 2015
• 22mPython for science, side projects and stuff!Andrew Lonsdale · PyCon AU 2016
• 27mSentiment analysis of tweets in Polish language using deep...Joanna Piwko · PyData Warsaw 2019