0.25
0.5
0.75
1.25
1.5
1.75
2
Semantic Topic Compass - Classification based on Unsupervised Feature Ambiguity Gradation
Published on Jul 28, 20161112 Views
Characterising social media topics often requires new features to be continuously taken into account, and thus increasing the need for classifier retraining. One challenging aspect is the emergence of
Related categories
Chapter list
Semantic Topic Compass 00:00
Outline00:12
Topic classification on twitter00:35
Approaches00:46
Classification features01:15
Feature selection02:31
Ambiguity in Topic Classification (1)03:22
Ambiguity in Topic Classification (2)04:49
Ambiguity measure feature selection method05:30
Semantic Topic Compass - 106:27
Semantic representation of topics' feature space07:17
Capturing contextual semantics07:58
Capturing Words’ Distributional Semantics08:37
Constructing the Topic’s Feature Space09:11
Extracting Topic Feature10:13
Feature Weighting & Classifier Training10:43
Conceptual Semantic Enrichment11:19
Experiments12:59
Datasets13:02
Results13:53
1. Feature Weighting with the STC Framework13:58
2. Cross Comparison Results - 115:18
2. Cross Comparison Results - 215:34
Conclusion16:37
Thank you17:30