A Recommendation Method for Recipes Containing Unskillful Elements using Naïve Bayes Classifier to Improve Cooking Skills
Xinyu Liu, Daisuke Kitayama
The 24th International Conference on Information Integration and Web Intelligence (iiWAS2022), pp.429-434, 2022年11月, 査読有
論文PDF
概要
We cannot acquire cooking skills overnight; although our skills can be improved through repeated practice. This study proposes a method to recommend recipes that amateurs should attempt to turn failures into successes, based on their logs of cooking failures and successes. Initially, the user classifies past recipes and labels them as failures and successes. Next, we use a naive Bayes classifier to find the factors of failures and successes from the recipe’s ingredients and cooking actions. By recommending recipes with multiple success factors and some failure factors, we aim to lower the psychological hurdle for attempting recipes with difficult factors that have resulted in failure earlier.