COGNITIVE INFORMATION RETRIEVAL

COGNITIVE INFORMATION RETRIEVAL

Cognitive refers to being in or relating to thinking, perceiving, understanding and learning. Information retrieval is obtaining knowledge from a collection of resources. The way in which humans search for information and the expected structure of retrieved information can vary from person to person. So combining both, that is Cognitive information retrieval is the phenomenon of understanding and learning the search pattern of a human, in order to optimize search results. The database can also be designed in an optimum way that makes query search easier.

The current IR systems work on improving the matching between the query and the documents that are retrieved, but cognitive IR works on understanding the cognitive behaviour of the user and his problem situation.

Figure 1 depicts the how different cognitive origins transforms the IR space.

Figure 1: Cognitive model for IR systems[2]

Key concepts of Cognitive IR

1.     Relevance: how the matching algorithm is updated in order match accurately the current need of the user rather than what he initially stated and the retrieved documents.

2.     Cognitive and interactive: captures the behaviour of the user towards the retrieved documents. How the user selects and wants the information that is retrieved to be structured.

3.     Poly – representational approach: describes user and a document representation, which are then checked for cognitive overlap. For the user, the poly-representation consists of the user’s various concurrent information needs, emotional states, tasks, organizational constraint etc. — a multipronged representation of the user’s cognitive space. For the document set, the poly-representation consists of the citation links, thesaurus terms, selectors (e.g., journal name, etc.), indexers terms and author’s headings, captions, etc.—a multipronged representation of the document set[3].

Various cognitive models

1.     Berrypicking: how the user cognitive of the information changes upon going through the retrieved result.

2.     Exploratory search: how users refine their search queries upon receiving the result of the previously specified query.

3.     Natural language search: understanding how users formulate queries.

Reference :

[1] https://en.wikipedia.org/wiki/Cognitive_models_of_information_retrieval

[2] Ingwersen, Peter. "Cognitive perspectives of information retrieval interaction: elements of a cognitive IR theory." Journal of documentation 52, no. 1 (1996): 3-50.

[3] http://www.rroij.com/open-access/a-review-of-the-cognitive-information-retrieval-concept-process-and-techniques-46-50.php?aid=38180