Name
Title | ||
|---|---|---|
Aggregating Functionality, Use History, and Popularity of APIs to Recommend Mashup Creation. |
Abstract | ||
|---|---|---|
Creating mashups from existing Web APIs has provided an effective means to boost software reuse and approach the full potential of online programming resources. One of the key hindrance faced by mashup creation is to discover relevant APIs, especially due to the recent fast growth of Web APIs and the brief, unstructured API descriptions. In this paper, we propose a novel approach that recommends APIs to create a mashup given a free-form text description. We incorporate three heterogeneous but complimentary factors into the recommendation process: the functionality of an API, the usage history of the API by existing mashups, and the popularity of the API. We leverage probabilistic topic models to learn an API's functionality from its textual description and compute relevance between the API and the given mashup description. As most APIs lack a rich textual description, we extend the API discovery process by exploiting collaborative filtering to estimate the probability of an API being used by existing similar mashups. These two sources of information are then integrated through Bayes' theorem, which allows us to discover a set of functionally relevant APIs. The popularity of these APIs is then factored in to perform quality based ranking so that the best APIs can be recommended first. A comprehensive experimental study has been conducted on a real-world dataset to evaluate the efficiency and effectiveness of the proposed method. The result indicates that our method is efficient and provides better recommendation than other competitive methods. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1007/978-3-662-48616-0_12 | Lecture Notes in Computer Science |
Field | DocType | Volume |
Data mining,Web API,Mashup,World Wide Web,Collaborative filtering,Ranking,Computer science,Reuse,Probabilistic logic,Topic model,Business process discovery | Conference | 9435 |
ISSN | Citations | PageRank |
0302-9743 | 7 | 0.51 |
References | Authors | |
8 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Aditi Jain | 1 | 7 | 0.51 |
| Xumin Liu | 2 | 471 | 34.87 |
| Qi Yu | 3 | 770 | 55.65 |