Onomatopoeia appears much frequently in the word-of-mouth restaurant search site. In this paper, we first analyzed the relationship between food categories and onomatopoeias on the word-of-mouth restaurant search site. From the analysis, we found that the appearance of onomatopoeias and food categories are highly correlated. This fact indicates that na?ve way of using onomatopoeia as feature of restaurant makes the recommendation similar to food category based recommendation. This motivate us to develop sense related onomatopoeia based recommendation as senses plays an important role to enjoy food in restaurant. For the purpose, we propose an algorithm to collect sense related onomatopoeias from the web and produce serendipitous restaurant recommendation using sense related onomatopoeias as feature. We have conducted user test and the result shows that the recommendation using sense related onomatopoeia based recommendation satisfies 14 subjects from the viewpoint of serendipity, which is much larger than 3 subjects of food category based recommendation.