# A Systematic Review of Automated Query Reformulations in Source Code Search

arXiv: https://arxiv.org/abs/2108.09646 · HTML: https://mlsanity.com/paper/2108.09646/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 215 references that are in the map.
- First posted on arXiv 22 Aug 2021.

## Builds on (most cited first, 19 of 19)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Opportunities and Challenges in Code Search Tools](https://mlsanity.com/paper/2011.02297/) (2020)
- [Query Expansion Based on Crowd Knowledge for Code Search](https://mlsanity.com/paper/1703.01443/) (2017)
- [RACK: Automatic API Recommendation using Crowdsourced Knowledge](https://mlsanity.com/paper/1807.02953/) (2018)
- [Improving IR-Based Bug Localization with Context-Aware Query Reformulation](https://mlsanity.com/paper/1808.00594/) (2018)
- [SWIM: Synthesizing What I Mean](https://mlsanity.com/paper/1511.08497/) (2015)
- [Evaluating How Developers Use General-Purpose Web-Search for Code Retrieval](https://mlsanity.com/paper/1803.08612/) (2018)
- [The Forgotten Role of Search Queries in IR-based Bug Localization: An Empirical Study](https://mlsanity.com/paper/2108.05341/) (2021)
- [Improved Query Reformulation for Concept Location using CodeRank and Document Structures](https://mlsanity.com/paper/1807.04488/) (2018)
- [Effective Reformulation of Query for Code Search using Crowdsourced Knowledge and Extra-Large Data Analytics](https://mlsanity.com/paper/1807.08798/) (2018)
- [Automated Query Reformulation for Efficient Search based on Query Logs From Stack Overflow](https://mlsanity.com/paper/2102.00826/) (2021)
- [On the Use of Context in Recommending Exception Handling Code Examples](https://mlsanity.com/paper/1807.02261/) (2018)
- [QUICKAR: Automatic Query Reformulation for Concept Location using Crowdsourced Knowledge](https://mlsanity.com/paper/1807.02964/) (2018)
- [Why are Some Bugs Non-Reproducible? An Empirical Investigation using Data Fusion](https://mlsanity.com/paper/2108.05316/) (2021)
- [Exploring Query Categorisation for Query Expansion: A Study](https://mlsanity.com/paper/1509.05567/) (2015)
- [STRICT: Information Retrieval Based Search Term Identification for Concept Location](https://mlsanity.com/paper/1807.04475/) (2018)
- [Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge](https://mlsanity.com/paper/1903.07662/) (2019)
- [TextRank Based Search Term Identification for Software Change Tasks](https://mlsanity.com/paper/1807.02263/) (2018)

## Built on by (most cited first, 2 of 2)

- [Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization](https://mlsanity.com/paper/2512.07022/) (2025)
- [Improved Bug Localization with AI Agents Leveraging Hypothesis and Dynamic Cognition](https://mlsanity.com/paper/2601.12522/) (2026)

## Abstract (arXiv)

Fixing software bugs and adding new features are two of the major maintenance tasks. Software bugs and features are reported as change requests. Developers consult these requests and often choose a few keywords from them as an ad hoc query. Then they execute the query with a search engine to find the exact locations within software code that need to be changed. Unfortunately, even experienced developers often fail to choose appropriate queries, which leads to costly trials and errors during a code search. Over the years, many studies attempt to reformulate the ad hoc queries from developers to support them. In this systematic literature review, we carefully select 70 primary studies on query reformulations from 2,970 candidate studies, perform an in-depth qualitative analysis (e.g., Grounded Theory), and then answer seven research questions with major findings. First, to date, eight major methodologies (e.g., term weighting, term co-occurrence analysis, thesaurus lookup) have been adopted to reformulate queries. Second, the existing studies suffer from several major limitations (e.g., lack of generalizability, vocabulary mismatch problem, subjective bias) that might prevent their wide adoption. Finally, we discuss the best practices and future opportunities to advance the state of research in search query reformulations.