Abstract: Books play a very important role in every person’s life by introducing them to a world of imagination, providing knowledge of the outside world, improving their reading, writing, and speaking skills as well as boosting memory and intelligence, all of which are quite necessary for different aspects of life. There exist many potential readers, but due to the abundance of information present on the internet, many of these people find it extremely hard to search for books that they might like and might inculcate in them a habit of reading, which is always encouraged. This could result in a huge loss as a lack of readings results in poor language skills, cultural ignorance, and fear of books. Furthermore, many people ask for book recommendations from their friends, neighbors, and families who might not always suggest the right book as they do not have knowledge about the numerous books that are available. If we plan to buy any new book, we normally ask our friends, research about the book, check the book ratings on the internet, find books that have similar content, and then we make our decision. How convenient if all this process was taken care of automatically and recommend the book efficiently? A recommendation system is an answer to this question. Recommendation System (RS) is software that suggests similar items to a purchaser based on their earlier purchases or preferences. The amount of information available on the internet is quite a lot and finding relevant information can become very difficult. Recommendation systems aim to solve such kinds of problems. With the help of recommendation systems, we can find relevant information quickly and easily. Many recommendation systems are also used in commercial websites to sell their products. Consequently, the main aim of our paper is to build a book recommendation web application. The web application can be used by anyone and does not require any login making it much more accessible and easy to use. The user needs to just enter the title of the book that they have read and liked before, and based on the genre and average rating given to the book. The top ten books will be recommended to the user that is the most similar to the book that they have entered.
The technologies used in this paper would be the python programming language for preprocessing the data, exploring the data, and building the machine learning model itself. Many python modules such as pandas and matplotlib and seaborn will be used for handling and visualizing the data. The algorithm that will be used to find books similar to the book entered by the user is the K-Means nearest neighbor algorithm. To provide a proper and appealing interface, this project is going to be a web application that will be developed using Flask. The initial exploration and preprocessing of the data will be done through Google Colab. The dataset used is ‘books_1.Best_Books_Ever’ from the ‘Goodreads’ dataset that contains attributes such as booke, title, author, rating, ISBN, genres, characters, awards, num ratings, ratingByStars, setting, bbeScore, bbeVotes etc.
Keywords: K-Means nearest neighbor; machine learning; Books; Receommendation;
|
DOI:
10.17148/IJARCCE.2022.11602
