Mapping of open-answers using machine learning

Sammanfattning: This thesis investigates if a model can be created to map misspelled answers from open-ended questions to a finite set of brands. The data used for the paper comes from the company Nepa that uses open-questions to measure brand-awareness and consists of misspelled answers and brands to be mapped to. A data structure called match candidate was created and consists of a misspelled answer and brand that it poten-tially be mapped to. Features for the match candidates were engineered and based on the edited distances, posterior probability and common misspellings among other. Multiple machine learning models were tested for classifying the match candidates as positive if the mapping was correct and negative otherwise. The model was tested in two scenarios, one when the answers in the training and testing data came from the same questions and secondly when they came from different ones. Among the classifiers tested, the random forest model performed best in terms of PPV as well as sensitivity. The resulting mapping identified on average 92% of the misspelled answers and map then with 98% accuracy in the first scenario. While in the second scenario 70% of the answers were identified with 95% confidence in the mapping on average.