Companion code for Awe the Audience: How the Narrative Trajectories Affect Audience Perception in Public Speaking
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
TED_stats
bluemix_sentiment
talks
.gitignore
LICENSE
README
TED Talks as of 02.07.2017.csv
TED_data_location.py
bluemix.py
bluemix_key.py
index.csv
index.xls
list_of_talks.py
requirements.txt
ted_talk_cluster_analysis.py
ted_talk_experiments.py
ted_talk_new_crawler.py
ted_talk_prediction.py
ted_talk_sentiment.py
ted_talk_statistic.py
ted_talk_statistic_correlation.py

README

Companion code for
Awe the Audience: How Emotional Trajectories Affect Audience Perception in Public Speaking

Installation Instruction
========================
1. For python distribution, you can install anaconda or miniconda (a mini version of anaconda)
https://conda.io/docs/user-guide/install/index.html

2. Install the requirements:
pip install -r requirements.txt

3. Install IBM Watson Developer Cloud to extract the tone (Emotion, Language, Personality) scores:
pip install --upgrade watson-developer-cloud
For more instructions/help, you may visit: https://pypi.python.org/pypi/watson-developer-cloud


4. (Optional) If you want to extract the IBM scores yourself, you need to create an account for IBM Watson tone analyzer service (Even a free account will work):
https://www.ibm.com/watson/services/tone-analyzer/
Then, edit the bluemix_key.py file and put the credentials (username and password) provided in the service key. Please note that this credentials are different than your account login username and password.
 

Please Note: We provided the TED talk transcripts and the IBM scores within the repository (please check the talks folder and the bluemix_sentiment folder. The data is stored in pickle format. To unpickle and to see the data, use the pickle library in python: https://docs.python.org/2/library/pickle.html)

Usage
=====
cd tedanalytics
python ted_talk_experiments.py

Documentation
=============
All the codes are documented inline