“…Content-based recommender systems base their recommendations on the similarity between new items, liked by users before, which described items with metadata and extracted features. Examples of content-based recommender systems are: Yuan and Cheng (Yuan & Cheng, 2004) presented a one-to-one recommendation mechanism that iteratively took inputs of the audio customer messages and produces personalized product analog structures deriving the generation of personalized heterogeneous products based on the coupled clustering algorithm; Blanco-Fernandez, Pazos-Arias, Gil-Solla, Ramos-Cabrer, and Lopez-Nores (2008) presented a personalization strategy that overcame the unresolved limitation of the existing recommender systems, i.e., overspecialization, by applying reasoning techniques borrowed from the semantic web; and Chang, Chen, Chiu, and Chen (2009) proposed an approach that trained the artificial neural networks to group users into different clusters and applied the well-established Kano's method to extracting the implicit needs from users in different clusters for improving information overloading in a real case of tour and travel websites.…”