ARSeek: Identifying API Resource Using Code and Discussion on Stack Overflow

Sun, 01 May 2022 00:00:00 +0000

Overview

When developers look for API resources, they rely on two complementary information sources: code (showing how an API is called) and discussion (explaining why and when to use it). ARSeek is a retrieval system that jointly exploits both modalities from Stack Overflow to identify the most relevant API resources for a given developer query.

Approach

Code signal: Extracts API call patterns and signatures from Stack Overflow answer code blocks, matched against query API names and contexts.
Discussion signal: Applies PTM-based semantic analysis to Stack Overflow post bodies and titles to understand the conceptual relevance of each post to the query.
Joint ranking: Fuses both signals into a unified ranking model that outperforms either modality used alone.

Key Results

ARSeek consistently outperforms code-only and text-only baselines on the API resource identification benchmark, demonstrating that the two modalities provide complementary signals that are stronger in combination.

Published at: IEEE/ACM International Conference on Program Comprehension (ICPC) 2022 · Citations: 6

FACOS: Finding API Relevant Contents on Stack Overflow with Semantic and Syntactic Analysis

Mon, 01 Nov 2021 00:00:00 +0000

Overview

Stack Overflow is the primary resource for developers seeking API usage examples, error explanations, and best practices. However, finding the most relevant posts for a specific API query remains a challenge — keyword search often surfaces too many irrelevant results, while semantic search alone misses syntactically precise matches.

FACOS (Finding API Contents On Stack Overflow) addresses this by combining:

Semantic analysis: leveraging PTMs to understand the intent behind API-related queries and map them to conceptually similar Stack Overflow discussions.
Syntactic analysis: using code structure and API call signatures to identify posts with exact or near-exact API usage patterns.

Approach

FACOS fuses both signals into a unified ranking model, trained and evaluated on a curated benchmark of API queries paired with their ground-truth relevant Stack Overflow posts. The hybrid approach consistently outperforms pure semantic and pure syntactic baselines.

Published at: arXiv preprint arXiv:2111.07238, 2021 · Citations: 7

Khanh Luong | Mohammad Abdul Hadi

ARSeek: Identifying API Resource Using Code and Discussion on Stack Overflow

Overview

Approach

Key Results

FACOS: Finding API Relevant Contents on Stack Overflow with Semantic and Syntactic Analysis

Overview

Approach