Center for Process Innovation Colloquium Series
Workshop on Text Mining
Presented in Collaboration with the Institute for Insight
- Hosted by: Center for Process Innovation (CEPRIN) in collaboration with the Institute for Insight
- Location: Room 304, GSU Buckhead Campus
- Time: December 4, 2015 (2:00 pm - 4:00 pm)
- Speaker: Zhitao Yin
- Workshop developed with the guidance of Dr. Arun Rai
- Concept: Introduce text preparation, lexicon-based word counting, algorithm-based word counting, and topic modeling.
- Application: Demonstrate how to use Python to apply these techniques to Yelp review dataset.
- Experience: Give students hands-on experience through three exerises during the workshop.
- Natural Language Processing with Python by Bird et al., 2009.
- Narrative Framing of Consumer Sentiment in Online Restaurant Reviews by Jurafsky et al., 2014.
- Probabilistic Topic Models by David Blei, 2012.
- Please follow the instructions to set up your Python environment.
- Lecture Slides
- Please download the Code Package which includes demo code, demo dataset, exercise questions, and exercise dataset.
- Once downloaded, please extract the "code package" under your iPython notebook working directory.
- Click here to view the code online if you do not have iPython notebook installed in your computer.
- We will have three exerises during the workshop. For each of them, I will invite one group to present their results. The results will be posted on Exercise Slides.
Please take a few minutes to answer the feedback questionnaire at the completion of the workshop.