Active stream learning is frequently used to acquire labelsfor instances and less frequently to determine which features should beconsidered as the stream evolves. We introduce a framework for activefeature selection, intended to adapt the feature space of a polarity learnerover a stream of opinionated documents. We report on the first results ofour framework on substreams of reviews on different product categories.
%0 Conference Paper
%1 shivakumaraswamy19
%A Shivakumaraswamy, Ranjith
%A Beyer, Christian
%A Unnikrishnan, Vishnu
%A Ntoutsi, Eirini
%A Spiliopoulou, Myra
%B Proceedings of the Workshop on Interactive Adaptive Learning (IAL 2019)
%D 2019
%K active-learning kmd stream-mining
%P 108--111
%T Active Feature Acquistion for Opinion Stream Classification under Drift
%U http://ceur-ws.org/Vol-2444/ialatecml_shortpaper3.pdf
%X Active stream learning is frequently used to acquire labelsfor instances and less frequently to determine which features should beconsidered as the stream evolves. We introduce a framework for activefeature selection, intended to adapt the feature space of a polarity learnerover a stream of opinionated documents. We report on the first results ofour framework on substreams of reviews on different product categories.
@inproceedings{shivakumaraswamy19,
abstract = {Active stream learning is frequently used to acquire labelsfor instances and less frequently to determine which features should beconsidered as the stream evolves. We introduce a framework for activefeature selection, intended to adapt the feature space of a polarity learnerover a stream of opinionated documents. We report on the first results ofour framework on substreams of reviews on different product categories.},
added-at = {2020-01-13T10:12:57.000+0100},
author = {Shivakumaraswamy, Ranjith and Beyer, Christian and Unnikrishnan, Vishnu and Ntoutsi, Eirini and Spiliopoulou, Myra},
biburl = {https://www.bibsonomy.org/bibtex/2b6fd8a2002452bc6fbf49e17e57ada9c/kmd-ovgu},
booktitle = {Proceedings of the Workshop on Interactive Adaptive Learning (IAL 2019)},
interhash = {04ed309a42ac203063ca870ac3005208},
intrahash = {b6fd8a2002452bc6fbf49e17e57ada9c},
keywords = {active-learning kmd stream-mining},
organization = {CEUR Workshop},
pages = {108--111},
timestamp = {2020-01-13T10:12:57.000+0100},
title = {Active Feature Acquistion for Opinion Stream Classification under Drift},
url = {http://ceur-ws.org/Vol-2444/ialatecml_shortpaper3.pdf},
year = 2019
}