Database and Expert Systems Applications. 8th International Conference, DEXA '97. Proceedings
DOI: 10.1109/dexa.1997.617331
|View full text |Cite
|
Sign up to set email alerts
|

Applying evolutionary algorithms to the problem of information filtering

Abstract: This paper presents an intelligent ittformatioti filtering system that learns f r o m m e r feedback and behavior through evolrrtiotiary nlgorithms. By applying the learning abilities of a Classifier System and Genetic Algorithms to the system the follobvitig tasks can be performed:( I ) reducing a user's information overload (2) predicts the actions that the users are supposed to( 3 ) prioritizing of emails do and

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
7
0
1

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 11 publications
(8 citation statements)
references
References 5 publications
0
7
0
1
Order By: Relevance
“…In Min Tjoa et al [21], is presented a system called CIFS (Cognitive Information Filtering System) which applies an evolutionary model (Learning Classifier System) at the time of to learn from the user. CIFS filter e-mails, based in the ranking that do the user and in the checking of behaviour of him.…”
Section: Related Workmentioning
confidence: 99%
“…In Min Tjoa et al [21], is presented a system called CIFS (Cognitive Information Filtering System) which applies an evolutionary model (Learning Classifier System) at the time of to learn from the user. CIFS filter e-mails, based in the ranking that do the user and in the checking of behaviour of him.…”
Section: Related Workmentioning
confidence: 99%
“…Typically, evolutionary AIF systems maintain a population of profiles that collective represent a user's interests. The most common practice is to represent profiles and documents as weighted keyword vectors in a vector space with as many dimensions as the number of unique words in the documents' vocabulary [7], [8], [9]. Alternative representations, such as weighted trigram 1 vectors also exist [10], [11], but are outside the scope of the current work.…”
Section: Evolutionary Information Filteringmentioning
confidence: 99%
“…1): single-point [12], two-point [9], [7] and three-point [13]. More crossover points means more randomness, which can destroy important keyword combinations resulting in less successful individuals [8]. More randomness can result in performance fluctuations and the user's dissatisfaction.…”
Section: Evolutionary Information Filteringmentioning
confidence: 99%
See 1 more Smart Citation
“…En Min Tjoa et al [11], se presenta un sistema denominado CIFs (Cognitive Information Filtering System) el cual aplica un modelo evolutivo (sistema clasificador de aprendizaje) a la par que aprende de la realimentación del usuario. CIFS filtra correos electrónicos en el basado en el ranqueo que hace el usuario a los correos y también en base a la monitorización del comportamiento del mismo.…”
Section: Trabajo Relacionado De Aplicaciones De Algoritmos Evolutivosunclassified