Abstract: The purpose of this paper is to provide empirical evidence that the design science framework Information System Research (ISR) works in practice. More than ten years has passed since ISR was published in the well‑cited article ‘Design Science in Information Systems Research’. However, there is no thoroughly documented evaluation of ISR based on primary data. That is, existing evaluations are based on reconstructions of prior studies conducted for other purposes. To use an existing data set to answer new or extended research questions means to conduct a secondary analysis. We point to several risks related to secondary analyses and claim that popular design science research frameworks should be based on primary data. In this paper, we present an evaluation consisting of empirical experiences based on primary data. We have systematically collected experiences from a three‑year research project and we present ting of both strengths and weaknesses are presented. The main strengths are: the bridging of the contextual environment with the design science activities and the rigorousness of testing IT artefacts. The main weaknesses are: imbalance in support for making contributions to both theory and practice, and ambiguity concerning the practitioners’ role in design and evaluation of artefacts. We claim that the identified weaknesses can be used for further development of frameworks or methods concerning design science research.

Given the challenges associated with the analysis of emotions in text by counsellors, we present an intelligent e‑counselling system for automatic detection of emotions and sentiments in text. The system‑ EmoTect‑ was developed using a supervised support vector machine learning classifier. Therefore, students’ life stories were collected and developed into a corpus for training and evaluating of the classifier. EmoTect allows users to label instances of the training data based on their own perception of emotions, and then gradually learns to classify emotions according to the user’s perceptions. The EmoTect interface provides a visualization of the emotional changes from automatically analysed students’ submissions over a selectable period. In this paper, the EmoTect classifier is evaluated with a gold standard corpus obtained from students but annotated by counsellors. In addition to the classifier evaluation, the EmoTect prototype was evaluated with counsellors in their settings. From the experimental results, the EmoTect classifier for the sentiment classification achieved comparable accuracy to that achieved with a gold standard when presented with unknown data. The contextual evaluation of the system indicates counsellors' satisfaction and sense of enthusiasm for using EmoTect for counseling delivery.