Intelligent Database Systems Lab Presenter : JHOU, YU-LIANG Authors :Shady Shehata, Fakhri Karray, Mohamed S. Kamel, Fellow 2012, IEEE An Efficient Concept-Based

Intelligent Database Systems Lab

Presenter : JHOU, YU-LIANG

Authors :Shady Shehata , Fakhri Karray, Mohamed S. Kamel, Fellow

2012, IEEE

An Efficient Concept-Based Mining Model for Enhancing Text Clustering


Outlines

MotivationObjectivesMethodology EvaluationConclusionsComments


Motivation• In text mining ,the term frequency is

computed to explore the importance of the term in document.

• However, two terms can have the same frequency in documents, but one term contributes more to the meaning of its sentences than the other term.


ObjectivesUsing Concept-Based Mining Model for Text Clustering , improve the clustering quality.


Methodology Concept-Based Mining Model


Methodology CONCEPT-BASED MINING MODEL

Ex: a concept c which appears twice in document d in the first and the second sentences The concept c appears five times in the verb argument structures of the first sentence s 1 , and three times in the verb argument structuresof the second sentence s 2 . ans : ctf value = (5+3)/2=4


MethodologyCorpus-Based Concept Analysis Algorithm


Methodology Example of Conceptual Term Frequency

. [ARG0 Texas and Australia researchers] have [TARGET created] [ARG1 industry-ready sheets of materials made from nanotubes that could lead tothe development of artificial muscles].

[ARG1 materials] [TARGET made ] [ARG2 from nanotubes that could leadto the development of artificial muscles].

[ARG1 nanotubes] [R-ARG1 that] [ARGM-MOD could] [TARGET lead] [ARG2 to the development of artificial muscles].



1. First verb argument structure for the verb created:. [ARG0 Texas and Australia researchers]. [TARGET created]. [ARG1 industry-ready sheets of materials madefrom nanotubes that could lead to the development of artificial muscles].

2. Second verb argument structure for the verb made:. [ARG1 materials]. [TARGET made]. [ARG2 from nanotubes that could lead to the development of artificial muscles].

3. Third verb argument structure for the verb lead:. [ARG1 nanotubes]. [R-ARG1 that]. [ARGM-MOD could]. [TARGET lead]. [ARG2 to the development of artificial muscles].


MethodologyExample of Conceptual Term Frequency

1. Concepts in the first verb argument structure of the verb created:. Texas Australia researchers. created. industry-ready sheets materials nanotubes lead development artificial muscles

2. Concepts in the second verb argument structure of the verb made:. materials. nanotubes lead development artificial muscles

3. Concepts in the third verb argument structure of the verb lead:. nanotubes. lead. development artificial muscles.




Methodology Concept-Based Similarity Measure


Experimental Result


Experimental Result


Experimental Result


Experimental Result


Conclusions

The new approach enhance text clustering quality.


CommentsAdvantages Improve the text clustering quality.Applications -Concept-based mining model -Conceptual term frequency

Documents

Intelligent Database Systems Lab Presenter : JHOU, YU-LIANG Authors :Shady Shehata, Fakhri Karray, Mohamed S. Kamel, Fellow 2012, IEEE An Efficient Concept-Based