A Java tool to automatically recognize natural language fragments in user reviews that are relevant for developers to evolve their applications.
ARdoc (App Reviews Development Oriented Classifier) is a Java tool that automatically recognizes natural language fragments in user reviews that are relevant for developers to evolve their applications. Specifically, natural language fragments are extracted according to a taxonomy of app reviews categories that are relevant to software maintenance and evolution. The categories were defined in our previous paper entitled "How Can I Improve My App? Classifying User Reviews for Software Maintenance and Evolution" ) and are: (i) Information Giving, (ii) Information Seeking, (iii) Feature Request and (iv) Problem Discovery. ARdoc implements an approach that merges three techniques: (1) Natural Language Processing, (2) Text Analysis and (3) Sentiment Analysis to automatically classify app reviews into the proposed categories. The purpose of ARdoc is to capture informative user reviews (requesting a new feature, description of a problem, or proposing a solution) and consequently to allow developers to better manage the information contained in user reviews.
How to use ARdoc
ARdoc Demonstration Video:
Sebastiano Panichella, Andrea Di Sorbo, Emitza Guzman, Corrado Aaron Visaggio, Gerardo Canfora and Harald Gall: How Can I Improve My App? Classifying User Reviews for Software Maintenance and Evolution. In Proceedings of the 31st International Conference on Software Maintenance and Evolution (ICSME 2015), Bremen, Germany, Sep 29 - Oct 1, 2015.
Appendix of the ARdoc evaluation:
Pdf of the Appendix.
The ARdoc tool with a user-friendly GUI (JRE 7 or higher required). Please read the README.txt file contained in the downloaded file to learn how to run the GUI. Download
Demo data set:
Some user reviews of "PowernAPP" app genereously made available by Benjamin Sautermeister. More info can be found at http://bsautermeister.de/powernapp/.
ARdoc java API
A java API for developers to easily integrate our tool in other java projects (The following picture explains how to use it). Download
Andrea Di Sorbo
University of Sannio, Italy
Gerardo Canfora University of Sannio, Italy