App stores allow users to give valuable feedback on apps, and developers to find this feedback and use it for the software evolution. However, finding user feedback that matches existing bug reports in issue trackers is challenging as users and developers often use a different language. In this work, we introduce DeepMatcher, an automatic approach using state-of-the-art deep learning methods to match problem reports in app reviews to bug reports in issue trackers. We evaluated DeepMatcher with four open-source apps quantitatively and qualitatively. On average, DeepMatcher achieved a hit ratio of 0.71 and a Mean Average Precision of 0.55. For 91 problem reports, DeepMatcher did not find any matching bug report. When manually analyzing these 91 problem reports and the issue trackers of the studied apps, we found that in 47 cases, users actually described a problem before developers discovered and documented it in the issue tracker. We discuss our findings and different use cases for DeepMatcher.

In the dynamic and fast-growing app market, monitoring and understanding how past releases are actually being used is indispensable for successful app maintenance and evolution. Current app usage analytics tools either log execution events, e.g., in stack traces, or general usage information such as the app activation time, location, and device. In this paper, we focus on analyzing the usages of the single app features as described in release notes and app pages. We suggest monitoring nine app-independent, privacy-friendly interaction events for training a machine learning model to learn app feature usages. We conducted a crowdsourcing study with 55 participants who labeled 5,815 feature usages of 170 unique apps for 18 days. Our within-apps evaluation shows that we could achieve encouraging precision and recall values already with ten labeled feature usages. For certain popular features such as browse newsfeed or send an email, we achieved F1 values above 88%. Betweenapps feature learning seems feasible with F1 values of up to 86%.

User comments have become an essential part of online journalism. However, newsrooms are often overwhelmed by the vast number of diverse comments, for which a manual analysis is barely feasible. Identifying meta-comments that address or mention newsrooms, individual journalists, or moderators and that may call for reactions is particularly critical. In this paper, we present an automated approach to identify and classify meta-comments. We compare comment classification based on manually extracted features with an end-to-end learning approach. We develop, optimize, and evaluate multiple classifiers on a comment dataset of the large German online newsroom SPIEGEL Online and the "One Million Posts" corpus of DER STANDARD, an Austrian newspaper. Both optimized classification approaches achieved encouraging F 0.5 values between 76% and 91%. We report on the most significant classification features with the results of a qualitative analysis and discuss how our work contributes to making participation in online journalism more constructive.