Change-proneness of software artifacts has been mainly related to the design characteristics and their previous history of changes. While these two aspects are essential and contribute significantly to the prediction, they leave out a critical factor: how the artifacts are being used. In the context of web APIs, consumers represent one of the main drivers of the change. Therefore, we propose a methodology for predicting the change-proneness of web API endpoint interfaces, taking into account not only design and change history but also their usage. Since the evolution of web APIs is and should be usage-driven, the way consumers use an API affects the future changes implemented by providers. Consequently, consumers' usage behavior contains essential information that contributes to identifying endpoints that are more prone to change. By considering the reasons behind changes, we introduce a set of metrics comprising design and usage aspects to be used as variables in prediction. To demonstrate the usefulness of the approach we perform an initial evaluation using a real-world web API. We quantify the introduced metrics using web API documentation, code, and usage logs in order to build a classifier able to predict with 82 % accuracy if an endpoint will change based on its design, history of changes, and usage characteristics.

As the use of Application Programming Interfaces (APIs) is increasingly growing, their evolution becomes more challenging in terms of the service provided according to consumers’ needs. In this paper, we address the role of consumers’ needs in WAPIs evolution and introduce a process mining pattern-based method to support providers in WAPIs evolution by analyzing and understanding consumers’ behavior, imprinted in WAPI usage logs. We take the position that WAPIs’ evolution should be mainly usage-based, i.e., the way consumers use them should be one of the main drivers of their changes. We start by characterizing the structural relationships between endpoints, and next, we summarize these relationships into a set of behavioral patterns (i.e., usage patterns whose occurrences indicate specific consumers’ behavior like repetitive or consecutive calls), that can potentially imply the need for changes (e.g., creating new parameters for endpoints, merging endpoints). We analyze the logs and extract several metrics for the endpoints and their relationships, to then detect the patterns. We apply our method in two real-world WAPIs from different domains, education, and health, respectively the WAPI of Barcelona School of Informatics at the Polytechnic University of Catalonia (Facultat d’Informàtica de Barcelona, FIB, UPC), and District Health Information Software 2 (DHIS2) WAPI. The feedback from consumers and providers of these WAPIs proved the effectiveness of the detected patterns and confirmed the promising potential of our approach.

Application Programming Interfaces (APIs) are means of communication between applications, hence they can be seen as user interfaces, just with different kind of users, i.e., software or computers. However, the very first consumers of the APIs are humans, namely programmers. Based on the available documentation and the "ease of use" perception (sometimes led by corporate decisions and/or restrictions) they decide to use or not a specific API. In this paper, we propose a data-driven approach to measure web API usability, expressed through the predicted error rate. Following the reviewed state of the art in API usability, we identify a set of usability attributes, and for each of them we propose indicators that web API providers should refer to when developing usable web APIs. Our focus in this paper is on those indicators that can be quantified using the API logs, which indeed reflect the actual behaviour of programmers. Next, we define metrics for the aforementioned indicators, and exemplify them in our use case, applying them on the logs from the web API of District Health Information System (DHIS2) used at World Health Organization (WHO). Using these metrics as features, we build a classifier model to predict the error rate of API endpoints. Besides finding usability issues, we also drill down into the usage logs and investigate the potential causes of these errors.

Applications typically communicate with each other, accessing and exposing data and features by using Application Programming Interfaces (APIs). Even though API consumers expect APIs to be steady and well established, APIs are prone to continuous changes, experiencing different evolutive phases through their lifecycle. These changes are of different types, caused by different needs and are affecting consumers in different ways. In this paper, we identify and classify the changes that often happen to APIs, and investigate how all these changes are reflected in the documentation, release notes, issue tracker and API usage logs. The analysis of each step of a change, from its implementation to the impact that it has on API consumers, will help us to have a bigger picture of API evolution. Thus, we review the current state of the art in API evolution and, as a result, we define a classification framework considering both the changes that may occur to APIs and the reasons behind them. In addition, we exemplify the framework using a software platform offering a Web API, called District Health Information System (DHIS2), used collaboratively by several departments of World Health Organization (WHO).