MAICBR: A Multi-agent Intelligent Content-Based Recommendation System Aarti Singh and Anu Sharma Abstract This study aims at proposing an intelligent and adaptive mechanism deploying intelligent agents for solving new user and overspecialization problems that exist in Content Based Recommendation (CBR) systems. Since the system is designed using software agents (SAs), it ensures highly desired full automation in web recommendations. The proposed system has been evaluated and the results suggested that there is an improvement in positive feedback rate and the decrease in recommendation rate. Keywords Content ⋅ Ontology ⋅ Overspecialization ⋅ New user problem Recommendation ⋅ Semantic ⋅ Software agents 1 Introduction Adaptive web sites that provide personalized experience to web users are very effective in reducing the surfing time and searching the relevant information from internet [1]. Many techniques are discussed in literature to provide recommenda- tions to the user [2]. Some of the important techniques are CBR, Collaborative Filtering (CF), Case Based Filtering (CBF), hybrid, and intelligent recommendation techniques [3]. CBR considers the contents of items/web page for generating rec- ommendations to the web user. Some of the important drawbacks of CBR are limited content analysis, new user problem, and overspecialization. Many researchers [4–6] have put their efforts in solving these problems in CBR by proposing hybrid and intelligent techniques. With the advent of semantic web, orientation of web has been changed to knowledge provider rather than information dissemination medium. The amalgamation of semantic web technologies with A. Singh ( ✉ ) ⋅ A. Sharma MMICT & BM, Maharishi Markandeshwer University, Haryana, India e-mail: singh2208@gmail.com A. Sharma e-mail: anu@iasri.res.in © Springer Nature Singapore Pte Ltd. 2018 D.K. Mishra et al. (eds.), Information and Communication Technology for Sustainable Development, Lecture Notes in Networks and Systems 10, https://doi.org/10.1007/978-981-10-3920-1_41 399