Extracting Data from Tutorials for Android API Recommendation
Weizhao Yuan · Proceedings of the 2nd International Forum on Management, Education and Information Technology Application (IFMEITA 2017) · 2018
Code recommendation is becoming more and more important for software development because increasing numbers of existing libraries are being utilized by developers and code recommendation tools offer great aids to developers in quickly finding suitable APIs to use.There have been many studies on recommending various libraries and APIs for developers according to their requirements for certain functionalities, but little effort is spent in Android API recommendation.This study aims at building a database which stores the mapping co-relationships from Android APIs and their descriptive texts which describe the functionalities that can be achieved using the APIs.The data of such mapping co-relationships are extracted from online tutorials, and the database can be further used for recommending APIs for Android development by comparing the similarity between users' requirements and the descriptive texts in the database.