Systems Recommendation

According to Burke (2007), recommender system can be defined as a “personalized information agent that provides recommendation: suggestions for items likely to be of use to a user“. Similar with him, (Van Setten, Pokraev, & Koolwaaij, 2004) also yielded that recommender systems can be explained as systems capable of helping people to quickly and easily find their way through large amounts of information by determining what is of interest to a user.

There are several sources determining recommender system. Three of them are mentioned in her paper, namely background data, input data, and the algorithm that combines background data and input data (Hella, 2014). Background data is the information possessed by the system before the process of recommendation begins. Meanwhile, input data is the information that user communicates with the system.

Several recommendation techniques have been intensively researched resulting 4 basis automated recommendation techniques. They are collaborative, content-based, and knowledge-based, and demographic techniques (Burke, 2007). The details were explained below:
• Collaborative recommendation: The system only uses information about rating profiles for different users to generates recommendation.
• Content-based recommendation: The system is using 2 sources to generate recommendation. Those 2 sources are the features associated with products and the rating users has given to them.
• Demographic recommendation: The system provides recommendation based on demographic profile of the user.
• Knowledge based recommendation: The system provides recommendation based on inferences about a user’s needs and preferences.

Apart from those 4 techniques, there is also another technique proposed by Brunato, Battiti, Villani, & Delai (2002), namely context based recommender system. Context can be defined as any information that can be used to characterize the situation of any person, place or object that is considered relevant to the interaction between a user and an application, including the user and application themselves (Van Setten, Pokraev, & Koolwaaij, 2004). Several examples of context are location, time, proximity, user status, and network capabilities. In final, they mentioned that a context-aware system is “A system is context-aware if it uses context to provide relevant information and/or services to the user, where relevancy depends on the user’s task” (Van Setten, Pokraev, & Koolwaaij, 2004).

No matter what the type of recommender system, the final aim is for to provide a user with relevant information and/or services based on his current context. This goal matches with the goal of recommender systems which is helping people to quickly and easily find their way through large amounts of information by determining what is of interest to a user (Van Setten, Pokraev, & Koolwaaij, 2004). Therefore, in his paper, he tries to combine recommender systems and context-based to provide user with relevance information or services about tourism objects.

[archives limit=5]

Leave a Reply