Boosting API Recommendation with Implicit Feedback

Developers often need to use appropriate APIs to program efciently, but it is usually a difcult task to identify the exact one they need from a vast list of candidates. To ease the burden, a multitude of API recommendation approaches have been proposed. However, most of the currently available API r...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on software engineering Ročník 48; číslo 6; s. 1
Hlavní autoři: Zhou, Yu, Yang, Xinying, Chen, Taolue, Huang, Zhiqiu, Ma, Xiaoxing, Gall, Harald C.
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.06.2022
IEEE Computer Society
Témata:
Active learning
API recommendation
Application programming interface
Braiding
Feedback
Learning
learning to rank
natural language processing
Performance enhancement
User feedback
ISSN:0098-5589, 1939-3520
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Developers often need to use appropriate APIs to program efciently, but it is usually a difcult task to identify the exact one they need from a vast list of candidates. To ease the burden, a multitude of API recommendation approaches have been proposed. However, most of the currently available API recommenders do not support the effective integration of user feedback into the recommendation loop. In this paper, we propose a framework, BRAID (Boosting RecommendAtion with Implicit FeeDback), which leverages learning-to-rank and active learning techniques to boost recommendation performance. By exploiting user feedback information, we train a learning-to-rank model to re-rank the recommendation results. In addition, we speed up the feedback learning process with active learning. Existing query-based API recommendation approaches can be plugged into BRAID. We select three state-of-the-art API recommendation approaches as baselines to demonstrate the performance enhancement of BRAID measured by Hit@k (Top-k), MAP, and MRR. Empirical experiments show that, with acceptable overheads, the recommendation performance improves steadily and substantially with the increasing percentage of feedback data, comparing with the baselines.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0098-5589
1939-3520
DOI:10.1109/TSE.2021.3053111