TY - JOUR AU - Rehman Khan, Haseeb ur AU - Chen Kim, Lim AU - Shir Li, Wang PY - 2021/03/01 Y2 - 2024/03/29 TI - Contextual Suggestion and Recommendation Systems: A Review on Challenges in User Modeling and Privacy Concern: Sistem Kontekstual Cadangan dan Syor: Satu Tinjauan Terhadap Cabaran dalam Pemodelan Pengguna dan Masalah Privasi JF - Journal of ICT in Education JA - JICTIE VL - 8 IS - 1 SE - Articles DO - 10.37134/jictie.vol8.1.4.2021 UR - https://ojs.upsi.edu.my/index.php/JICTIE/article/view/5342 SP - 43-60 AB - <p><strong>Abstract</strong></p><p style="text-align: justify;">The contextual suggestion systems are emerging as modified recommendation systems integrated with information retrieval techniques to search within large databases with the purpose to provide a user with a list of suggestions based on context i.e. location, time of the day, any day of the week (weekdays or weekend). The goal of this research is to conduct a systematic review in the field of contextual suggestion and recommendation systems incorporate with smart cities as the repositories of large datasets. This paper highlights the concerns linked with approaches being used in the contextual suggestion system and discussing various approaches which are being utilized in the contextual suggestion system. The keywords for query searching include; “contextual suggestion”, “recommendation system” and “smart city” which identified 191 papers published from 2012 to 2020. Four major article repositories were considered for searching (i) Science Direct, (ii) Scopus, (iii) IEEE, and (iv) Web of Science. The review was conducted under the protocols of four phases (i) Query searching in major article’s repositories, (ii) remove duplicates, (iii) scan title and abstract, and (iv) complete article reading. To identify the gaps in ongoing research a taxonomy analysis was exemplified into categories which further divided into subcategories, the main categories are highlighted as (i) review articles, (ii) model/framework and, (iii) smart city and applications. The critical analysis highlighted the limitations of approaches being used in the field and discussed the challenges. The review also reveals that most researches utilized approaches based on content-based filtering, collaborative filtering, preference-based product ranking, language modelling, evaluation measures were precision, normalized discounted cumulative, mean reciprocal rank, and the test collection comprised of internet resources.</p> ER -