Article Preview
Top1. Introduction
The Internet is an enormous machine-Eco-system consisting of a lot of information. Processing this large quantity of information requires sophisticated methods which take care of efficiency in terms of processing time and space consumption. The science dealing with these methods and systems is called Information Retrieval. A part of Information Retrieval which deals with personalization is referred to as Information Filtering.
An Information filtering system is a system that removes redundant or unwanted information from an information stream using (semi)automated or computerized methods prior to presentation to a human user. Its main goal is the management of the information overload and increment of the semantic signal-to-noise ratio. Many IF systems have been developed in recent years for various application domains. Some examples of filtering applications are: filters for search results on the internet that are employed in the Internet software, personal e-mail filters based on personal profiles, list-servers or newsgroups filters for groups or individuals, browser filters that block non-valuable information, filters designed to give children access them only to suitable pages, filters for e-commerce applications that address products and promotions to potential customers only, and many more. These are semi- automated filters which can be configured and altered depending on the requirement. In this paper we emphasize on invisible or automatic filters which employ information filtering without the actual consent of the user using the system. To do this the user's profile is compared to reference characteristics which determine the relevance and filtering behaviour. These characteristics may originate from the information item (the content-based approach) or the user's social environment (the collaborative filtering approach) (Agichtein, Brill, & Dumais, 2006).
The key property of invisible filter is that one cannot tweak them based on certain parameters but the filter’s presence can be seen and felt by only looking at the behaviour of the system in which the filter is deployed. In this paper we analyse one such filter in a search engine through its behaviour. The usage and the results of Information Filters take a lot of forms. On the presentation level, information filtering takes the form of user-preferences-based newsfeeds, etc. Recommender systems are active information filtering systems that attempt to present to the user information items (film, television, music, books, news, web pages) the user is interested in. These systems add information items to the information flowing towards the user, as opposed to removing information items from the information flow towards the user. Use of Natural Language Processing, Data Mining and Machine Learning has increased the scope and power of Information Filtering (Asoh, Motomura, & Ono, 2010; Adar, Teevan, Dumais, & Elsas, 2009). Recommender systems typically use collaborative filtering (Herlocker, Konstan, Terveen, & Reidl, 2004) approaches or a combination of the collaborative filtering and content-based filtering approaches, although content-based recommender systems do exist.
Following are few of the versions of definitions of Information Filtering systems:
1.1. Basic Definition
“An Information filtering system is a system that removes redundant or unwanted information from an information stream using (semi)automated or computerized methods prior to presentation to a human user” -Wikipedia
1.2. A Security Based Definition
“On the Internet, content filtering (also known as information filtering) is the use of a program to screen and exclude from access or availability Web pages or e-mail that is deemed objectionable. Content filtering is used by corporations as part of Internet firewall computers and also by home computer owners, especially by parents to screen the content their children have access to from a computer” (Content Filter, n.d.).