Research paper

SCoR: an online Stack Overflow code recommender

A desktop application that takes a developer's question, collects Stack Overflow results in real time, then ranks and clusters the code snippets in the answers so the useful ones are quick to find.

Software engineering
Information retrieval
Clustering

The problem

Stack Overflow is one of the main places developers learn how to use libraries, APIs, and programming concepts. Finding the right answer often means reading through many results, which costs time and money.

Earlier tools such as Google Code Search, MAPO, and Strathcona re-rank code snippets, but each is limited to certain projects, APIs, languages, or IDEs.

How SCoR works

SCoR (Stack Overflow Code Recommender) is a desktop application with a graphical interface. It takes the user's query and a few other inputs, then:

collects Stack Overflow results in real time,
extracts the code snippets and other features from all the answers,
ranks the code snippets based on those features,
clusters similar answers into groups, and
recommends clusters of refined code snippets, with related comments where they exist.

Result

Initial evaluations showed a considerable reduction in the effort developers spent searching Stack Overflow results.

More research and earlier projects

See all

Research paper2020

Cutting stock with rotation: packing square items into square bins

A research paper on square packing, a two-dimensional version of bin packing where square items go into as few square bins as possible. Unlike earlier models, items may be rotated, which matches how stock cutting works in practice.

Research paper2021

On the fault-tolerant online bin packing problem (server consolidation)

A research paper on placing replicated tenants onto as few cloud servers as possible while staying safe when a server fails. Tenants arrive one at a time and can't be moved later, so this is an online bin packing problem with fault tolerance built in.

Data science2021

A sentiment analysis: predicting communicative intention in code review questions

Classification models that predict the intention behind a code review question, such as asking for a clarification, suggesting an improvement, or asking why something was built a certain way, using the question's words plus key-question, sentiment, and length features.

Have a project in mind?

Send a short note on what you're building. I'll reply with questions and a rough plan.

Start a project Email contact@pooya.website