Academia.eduAcademia.edu

Figure 8 – uploaded by Alejandro Cadenas

See full PDFdownloadDownload figure
Such data can be obtained from different collaborative servers across the Internet as we can see in Figure 9. The item description and the user rating of each item increases significantly day by day, being the geopositioned items one of the most common ones.

Figure 9 Such data can be obtained from different collaborative servers across the Internet as we can see in Figure 9. The item description and the user rating of each item increases significantly day by day, being the geopositioned items one of the most common ones.

Related Figures (14)

The rating function R introduced above is usually defined as a partial function, where the initial set of ratings is known. Then, as usual in recommender systems, the goal is to estimate the unknown ratings, i.e., make the rating function RA total. Visually, ratings A(d4,...d;) on the recommendation space S = D; x Dp x ...x D, can be stored in a multidimensional cube, such as the one shown in Figure 2. For example, the cube in Figure 2 stores ratings A(u,/,t) for the recommendation space Userxltemx Time, where the three tables define the sets of users, items and times associated with User, Item, and Time dimensions respectively.
The rating function R introduced above is usually defined as a partial function, where the initial set of ratings is known. Then, as usual in recommender systems, the goal is to estimate the unknown ratings, i.e., make the rating function RA total. Visually, ratings A(d4,...d;) on the recommendation space S = D; x Dp x ...x D, can be stored in a multidimensional cube, such as the one shown in Figure 2. For example, the cube in Figure 2 stores ratings A(u,/,t) for the recommendation space Userxltemx Time, where the three tables define the sets of users, items and times associated with User, Item, and Time dimensions respectively.
Figure 4 - Context-Aware architectures [reference 18]
Figure 4 - Context-Aware architectures [reference 18]
Figure 5 - Final phase of the contextual post-filtering approach: recommendation list adjustment [reference 18] For example, in a movie recommendation application, if a person wants to see a movie on a weekend, and on weekends she only watches comedies, the system can filter out all non-comedies from the recommended movie list. More generally, the basic idea for contextual post-filtering approaches is to analyze the contextual preference data for a given user in a given context to find specific item usage patterns (e.g., user Jane Doe watches only comedies on weekends) and then use these patterns to adjust the item list, resulting in more contextual’ recommendations, as depicted in Figure 5.
Figure 5 - Final phase of the contextual post-filtering approach: recommendation list adjustment [reference 18] For example, in a movie recommendation application, if a person wants to see a movie on a weekend, and on weekends she only watches comedies, the system can filter out all non-comedies from the recommended movie list. More generally, the basic idea for contextual post-filtering approaches is to analyze the contextual preference data for a given user in a given context to find specific item usage patterns (e.g., user Jane Doe watches only comedies on weekends) and then use these patterns to adjust the item list, resulting in more contextual’ recommendations, as depicted in Figure 5.
Figure 7 - Context acquisition diagram However, if such a system tries to get the contextual environment of the user ir order to provide better recommendations, it makes a big difference to get the contextual environment conditions of the potentially recommendable items. This way, the user’s context and the item context can be matched as a part of the recommendation mechanism itself, in order to get enhanced recommendatior results.
Figure 7 - Context acquisition diagram However, if such a system tries to get the contextual environment of the user ir order to provide better recommendations, it makes a big difference to get the contextual environment conditions of the potentially recommendable items. This way, the user’s context and the item context can be matched as a part of the recommendation mechanism itself, in order to get enhanced recommendatior results.
Figure 10 - Hybridizer Module This is a critical step that will impact the quality of the final results, so a step wise procedure is followed (Figure 10).
Figure 10 - Hybridizer Module This is a critical step that will impact the quality of the final results, so a step wise procedure is followed (Figure 10).
This proposal can be described into several phases as we can see on Figure 12.
This proposal can be described into several phases as we can see on Figure 12.
Table 2 - Algorithms results with a very low number of contents. The processing results are provided in next tables:
Table 2 - Algorithms results with a very low number of contents. The processing results are provided in next tables:
Table 3 - Algorithms results with a low number of contents.
Table 3 - Algorithms results with a low number of contents.
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved