The Big Bang Theory meets Deep Learning: The Emotion Annotation Episode

Join us for our 2nd community coding adventure in Deep Learning! Just bring your curiosity and get ready to meet our growing community 😀 We are using our collective expertise to start our 1st text annotation challenge. We will annotate the emotion behind each sentence in an episode of the popular TV show, The Big Bang Theory! Later on we will use these annotations to detect emotions using Deep Learning.

Join Zoom Meeting:
https://us02web.zoom.us/j/84402592502?pwd=d1lVSkxQZE1sSGljR3dXaEZwYmNEdz09

Phone: +1 929 205 6099 US
Meeting ID: 844 0259 2502

Agenda:

• Introductions and get to know our community

• Deep Learning YouTube recordings, feel free to share and subscribe 😀
  https://bit.ly/deep-learning-tf
  https://bit.ly/deep-learning-tf-coding

• Deep Learning Adventures - Coding Presentation:
  https://docs.google.com/presentation/d/1XXSLSTDOUnlYK1ksA4p3Kym-sDd7Nzj2r7__2fYqkxo/edit?usp=sharing

• Code repository for our Deep Learning Adventures 🎉
  https://github.com/georgezoto/Deep-Learning-Adventures

• Join us on Slack:
  https://join.slack.com/t/deeplearninga-nmk8930/shared_invite/zt-fupjj8pi-8Mb_D6dVRjTrrG9cktaehQ

• Spread the word about our meetup 🎉

• Coding session on real world data - Text Annotation
  Inspired by EmotionX 2019 SocialNLP Challenge
  http://doraemon.iis.sinica.edu.tw/emotionlines/index.html
  https://sites.google.com/view/emotionx2019/

• Step 1 😀
  Read more about emotions in text as well as the EmotionX 2019 Challenge from this paper and website:
  EmotionLines: An Emotion Corpus of Multi-Party Conversations
  https://arxiv.org/pdf/1802.08379.pdf
  SocialNLP: EmotionX 2019 Challenge where participants are challenged to predict the emotions induced by dialogue utterances by classifying each utterance into one of several labels
  https://sites.google.com/view/emotionx2019/

We will also reference these 2 sources in our 3rd coding challenge next week.

• Step 2 😀
  Familiarize yourself with award winning TV show: The Big Bang Theory https://en.wikipedia.org/wiki/The_Big_Bang_Theory

Specifically we will use Season 4, Episode 7 The Apology Insufficiency, as our text corpus. We will annotate a scene from this episode, line by line (or utterance as they are called in the EmotionLines paper)
https://docs.google.com/spreadsheets/d/1iXv-jMdHHdYziVgdWX23XLu2BaCuzKmy_mfosawdIVw/edit?usp=sharing

• Step 3 😀
  We will watch together this scene, pause and annotate it each sentence into one of these categories: neutral, joy, sadness, fear, anger, surprise, disgust.

We will also introduce a text annotation tool called doccano that can perform document classification, sequence labeling and sequence to sequence tasks: https://github.com/doccano/doccano

For simplicity and ease of use, tonight we will use a simple spreadsheet and later on we can use doccano to annotate larger corpora.

• Step 4 😀
  Based on demand from our group we can extend this annotation challenge longer offline and later revisit it to see if we can build a model that can predict emotions just from text.

• Step 5 😀
  Congratulations! You are well prepared to tackle coding challenge #3 where we will use 2,000 dialogues and 29K utterances to detect emotion from text using scripts from another award winning TV show, Friends!

Source:
https://arxiv.org/pdf/1802.08379.pdf
https://sites.google.com/view/emotionx2019
https://en.wikipedia.org/wiki/The_Big_Bang_Theory
https://bigbangtrans.wordpress.com/series-4-episode-07-the-apology-insufficiency
https://github.com/doccano/doccano
http://doccano.herokuapp.com