Evaluation of User-Subjective Web Interface Similarity with Kansei Engineering-Based ANN
2017 IEEE 3rd International Workshop on Usability and Accessibility focused Requirements Engineering (UsARE)
Ensuring similarity of user interfaces (UI) in software migration and redesign projects is often desirable to minimize re-learning effort for regular users and increase subjective satisfaction with new versions. In our paper we explore applicability of artificial neural networks (ANNs) to support test-driven development by predicting similarity assessments without employing the actual users. We identified two dimensions for similarity of user experience with web UIs: 1) objective, collected by a dedicated web intelligence miner (factors of page load speed, readability score, etc.) and 2) user-subjective, operationalized with the renowned Kansei Engineering method. Then we constructed the two respective ANN models predicting subjective similarity between websites of a same domain and trained the models with the data we collected in experimental sessions with 127 participants of different nationalities and 21 real university websites. The results of our pilot study suggest that subjective “emotional” factors are considerably more important in predicting similarity evaluations provided by users. Thus, employment of trained ANNs as test oracles may be feasible in automated measurement and control of UI similarity in migration and redesign.
Bakaev, Maxim; Heil, Sebastian; Khvorostov, Vladimir; Gaedke, Martin: Evaluation of User-Subjective Web Interface Similarity with Kansei Engineering-Based ANN. 2017 IEEE 3rd International Workshop on Usability and Accessibility focused Requirements Engineering (UsARE), pp. 125-131, 2017.