The rising number of students challenges the teacher’s time-consuming task to provide consistent and high-quality feedback for all students. To address the traditional education’s challenges, researchers refer to online educational tools to assist teachers. Although large writing tools (for instance, Grammarly and Microsoft Editor) assist students to write effectively, their primary objective is not to educate students. Therefore, we propose RevisionCoach – an automated writing feedback system that iteratively constructs educational, localized feedback to assist students to learn how to write. Clear and effective writing is important for students to succeed in academic endeavors and allows teachers to focus on feedback for the assignment’s primary task. RevisionCoach’s objective is to educate, and for that reason, the design considers learning by deliberate practice, differentiated learning, and self-regulated learning. In addition, RevisionCoach’s feedback has four layers: a sentence-level mistake highlight, an assessment category (coherence, cohesion, readability, and formality), a correction category (rewrite, reword, and rephrase), and a correction suggestion.

RevisionCoach’s categorized feedback allows for convenient evaluation that addresses RevisionCoach’s capability to predict the writing mistake’s importance. In the evaluation, we ask writing experts, students, Grammarly, and Microsoft Editor to find writing mistakes in text and to rate the mistake’s importance. Compared to the experts’ importance predictions, RevisionCoach predicts the mistake importances more accurately (1.89 mean square error (MSE)) than a random baseline (2.70 MSE), student baseline (2.50 MSE), Grammarly (2.52 MSE), and Microsoft Editor (2.02 MSE). Furthermore, the study illustrates the experts’ challenge to provide localized feedback for writing skills because the experts have merely 71.2% agreement about the top 2 most severe mistakes. At the same time, RevisionCoach achieves an average agreement of 72.9% with the experts’ mistake predictions.

Relive is a sports application that seeks to increase the retention rate of its user base. The project entails a route builder that can be incorporated in the Relive app. A route builder has several challenges, both in supporting user-friendly interaction, rendering the map and calculating the route. These challenges lead to design goals, such as a user experience focus, optimization of performance, and continuation of the project. To achieve these goals, the project is approached in an agile way with weekly planning meetings and tri-weekly stand-ups to keep it organized and well planned. The front-end features are based on a specific target audience: the Relive users that do not use a third party app for sporting activities. The screen is intuitive and supports storing of planned routes. A route can be created, edited and loaded in the Record functionality of the Relive app. To support the front-end, the back-end handles route calculation and route storing. The route calculation is done using Dijkstra’s shortest path algorithm. In addition, a proof of concept customized route calculation is created that focuses on popularity oriented routing. Route storing makes use of the internal databases of Relive and is integrated in the existing systems. Each feature is tested with automated end-to-end and unit tests. Additionally, user tests are performed to get valuable feedback from external users. Apart from active user participation, random users were selected to join a route builder experiment. During the project, more than 22 thousand users obtained the route builder feature. Each click is timed and tracked to make sure that the feature performed as expected. Based on the events and user surveys, another iteration of the application was made by making improvements based on the acquired information. These improvements are validated using event tracking to measure the desired improvements.