Analyzing the Preferences and Personal Needs of Teenage Readers to Make Book Recommendations

Reading is one of the main sources of learning, especially for young readers such as teens. Promoting good reading habits among teens is essential, given the enormous influence of reading on teenagers’ development as learners and members of society. For this reason, it is imperative to motivate young readers to read by offering them appealing books to read so that they can enjoy reading and gradually establish a reading habit during their formative years that can aid in enhancing their learning attitude. Books, which provide an indispensable source of reading materials, broaden the horizons of teenagers and allow them to learn from different disciplines, expand their perspective in decision making, and gain knowledge. These days there are a wide variety of books available on the market for teenagers, parents, and librarians to choose from. Due to the diversity of books, choosing a desirable book from a set of unfamiliar books to read is time-consuming and there is no guarantee of the satisfaction of its content. Existing book recommender systems, however, either focus on general audience or very young readers, such as children, and thus might not meet the specific needs of the particular group of users whom we target, i.e., teenagers. To make appropriate recommendations on books that are appealing to teenagers, we propose a book recommender system, called TBRec. TBRec recommends books to teenagers based on their personal preferences and needs that are determined by using various book features. These features, which include book genres, topic relevance, predicted user ratings, and readability levels, have significant impact on the readers’ preference and satisfaction on a book. These distinguished parts of a book identify the type, subject area, (un)likeness, and complexity of the book content. Experimental results reveal that TBRec outperforms Amazon, Barnes & Noble, and LibraryThing in making book recommendations for teenagers, and the results are statistically significant.