I. Groher, N. Seyff, T. Iqbal: Towards Automatically Identifying Potential Sustainability Effects of Requirements, 8th International Workshop on Requirements Engineering for Sustainable Systems (RE4SuSy), 27th IEEE International Requirements Engineering Conference (RE'19), Jeju Island, South Korea, Sept 23-27, 2019. paper

Software developers are gradually becoming aware that their systems have effects on sustainability. The identification of potential effects software-intensive systems can have on different sustainability dimensions over time is yet in its infancy. Researchers are currently exploring approaches which strongly make use of expert knowledge to identify potential effects. In this work in progress paper, we are looking at the problem from a different angle: we report on the exploration of a machine learning-based approach to identify potential effects. Such an approach allows to save time and costs but increases the risk that potential effects are overseen. First results of applying the machine learning-based approach in the domain of home automation systems are promising, but also indicate that further research is needed before our approach can be applied in practice. Furthermore, we have learned that even providing the ground truth for training the algorithms is a challenging task.


Towards Automatically Identifying Potential Sustainability Effects of Requirements