My name is Karen, and I am currently a Freshman at the University of Pennsylvania majoring in Computer Science.

​

I founded WeChat public account ShareSTEM 2 years ago with the goal of sharing valuable information and STEM learning resources with high school students. Now with 7000+ followrs, I feel the responsbility to make the account better.

​

This data project is divided into three parts.

​

1.  I used R notebook to analyze my own reader data. In this way, I hope to generate a more accurate reader profile - what they enjoy reading, what they pay the most attention to, etc.

​

2. Also using R notebook, I analyzed scraped data from a bigger and more successful WeChat public account (with similar target audience) to determine what are some "hot topics" among my target readers. In this way, I hope to make my current followers stay while letting my articles reach more potential readers.

 

3. Finally, since I am also planning on making ShareSTEM more "international" -- targeting at not just Chinese students who are interested in studying STEM -- I want to know what students care the most about when considering studying abroad. Thus, I scraped the "Student Experiences" blogs on Penn Abroad using Google Web Scraper, and did LDA modeling to determine what are some topics that are at the core of the studying-abroad experiences.