Computer science students mine software developer forums to teach coding practices

January 7, 2016, University of Delaware
Computer science students mine software developer forums to teach coding practices
Pictured are (from left) Zachary Senzer, Lori Pollock and Ryan Serva.

University of Delaware junior Zachary Senzer and senior Ryan Serva recently presented a research paper, "Automatically Mining Negative Code Examples from Software Developer Question and Answer Forums," at the Fourth International Workshop on Software Mining in Lincoln, Nebraska.

The paper was also published in the proceedings of the 2015 IEEE/ACM 30th International Conference on Automated Software Engineering Workshops (ASEW 2015).

Their research demonstrates how natural language processing and sentiment analysis techniques can be used to mine bad, or negative, code examples from developer forums to be used to help programmers in their learning and code improvement practices. 

Lori Pollock and Vijay Shanker, both professors in the Department of Computer and Information Sciences and co-authors of the paper, mentored Senzer and Serva in their research.

Senzer, an Honors Program student who is majoring in computer science with a minor in business administration, has been working with Pollock and Shanker at UD's Software Analysis and Compilation Lab since February 2014.

"Having the opportunity to present our research and hear from leaders in the software field was an invaluable experience," Senzer said. "It was fascinating to see how our work fits into the large-scale puzzle that researchers around the world are solving and refining."

Serva, a computer science major who joined the research lab in August 2014, said, "Working with this team has been a great experience. I learned so much, and was able to make a difference in an interesting field."

Serva's research experience complements his internship experience at Amazon, where he will be taking up a position after graduation in May.

Explore further: New DFG Grant proposal for a software quality control able to stand the test of time

Related Stories

Software 'Chipper' Speeds Debugging

October 1, 2007

Computer scientists at UC Davis have developed a technique to speed up program debugging by automatically "chipping" the software into smaller pieces so that bugs can be isolated more easily.

Next for DARPA: 'Autocomplete' for programmers

November 5, 2014

Writing computer programs could become as easy as searching the Internet. A Rice University-led team of software experts has launched an $11 million effort to create a sophisticated tool called PLINY that will both "autocomplete" ...

Recommended for you

Team breaks world record for fast, accurate AI training

November 7, 2018

Researchers at Hong Kong Baptist University (HKBU) have partnered with a team from Tencent Machine Learning to create a new technique for training artificial intelligence (AI) machines faster than ever before while maintaining ...


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.