China
Africa
Explore chapters and articles related to this topic
AI-Informed Analytics Cycle: Reinforcing Concepts
Published in Jay Liebowitz, Data Analytics and AI, 2020
Rosina O. Weber, Maureen P. Kinkela
Recommendation is the task that produces results in recommender systems. The idea is that from a base of items, such as products, services, individuals, or organizations, are recommended to a user. The user produces the input to the recommender that may include two categories of information, namely, user particular characteristics and item particular characteristics. Information about characteristics of the user are used to create a user profile or personalization. Information about the items to be recommended are usually features of these items that are called preferences. Recommendation is an analysis task because the features of the item are analyzed with the features of the user and their preferences in order to identify an item to be recommended. The input of recommender systems is usually users, items, and preferences.
IPTV Services Personalization
Published in Hassnaa Moustafa, Sherali Zeadally, Media Networks: Architectures, Applications, and Standards, 2016
Hassnaa Moustafa, Nicolas Bihannic, Songbo Song
The IPTV profile contains information helping the consumption of the different types of IPTV service like broadcast, Content on Demand (CoD), and network PVR service profiles. The European Telecommunications Standards Institute/Telecommunication and Internet converged Services and Protocols for Advanced Network (ETSI/TISPAN) defines three types of IPTV profiles [2]: Content Profile, Service Profile, and User Profile. Content profile contains and maintains information about multimedia meta-data and multimedia service packaging used for the provisioning of IPTV services. Service profile refers to data used to provide the service to the user (service-level user data such as user identification, numbering, addressing, security, and so on, and service-level offer data allowing the delivery of IPTV services, for example, EPG “Electronic Program Guide”/BPG “Broadcast Program Guide”). User profile refers to user customization and usage metadata containing and maintaining basic user information, service-specific information (subscription, bookmarks, activities, parental control, etc.) and user actions related to service purchase and consumption.
Portal Collaboration, Knowledge Management, and Personalization
Published in Shailesh Kumar Shivakumar, and User Experience Platforms, 2015
The basis for personalization is collecting and maintaining information regarding users. The collection of all the pieces of information relating to one user is referred to as a user profile. User information can be collected either directly from the user (via a user profile attribute) or from other sources such as tracking the user’s online activities. Users can be grouped into categories to facilitate personalization (which is sometimes referred to as “user segmentation”).
Fifteen Years of Recommender Systems Research in Higher Education: Current Trends and Future Direction
Published in Applied Artificial Intelligence, 2023
Vusumuzi Maphosa, Mfowabo Maphosa
(Upendran et al. 2016) developed an RS course to assist students entering college by using the student’s legacy data and data from students who have completed the course to address some of the challenges. The model is premised on the fact that when a student with a specific demographic and set of skills passes a particular course, then a student with the same abilities and demographic information is likely to pass that course. As students enter college, they have inadequate information about their courses and are often confused; RS can assist students in choosing courses through data mining techniques to uncover relationships with other students who graduated (Bendakir and Aïmeur 2006). (Maphosa, Doorsamy, and Paul 2020) recommended the creation of accurate user profiles by employing deep learning techniques such as convolutional networks, restricted Boltzmann machines, deep belief networks and stacked auto-encoders. More precise user profiles lead to more accurate recommendations.