%0 Conference Paper %1 noauthororeditor %A Beyer, Christian %A Unnikrishnan, Vishnu %A Niemann, Uli %A Matuszyk, Pawel %A Ntoutsi, Eirini %A Spiliopoulou, Myra %B Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing %D 2019 %I ACM %K entity-centric-learning kmd stream-mining %P 564-573 %R https://doi.org/10.1145/3297280.3297333 %T Exploiting Entity Information for Stream Classification over a Stream of Reviews %U https://doi.org/10.1145/3297280.3297333 %X Opinion stream classification algorithms adapt the model to the arriving review texts and, depending on the forgetting scheme, reduce the contribution old reviews have upon the model. Reviews are assumed independent, and information on the entity to which a review refers, i.e. to the opinion target, is thereby ignored. This implies that the prediction of a review's label is based more on reviews referring to other, more popular or simply more recently inspected entities, while reviews referring to the same entity might be ignored as too old. In this study, we enforce that the reviews to each entity are taken into account for learning, adaption and forgetting. We split the original stream to substreams, each substream comprised by the reviews referring to the same entity (opinion target). This allows us to deal with differences in the speed of each sub-stream and to exploit the impact of the entity itself on the labels of the reviews referring to it. For this constellation of substreams we propose a pair of two voting classifiers, one being the global, "entity-ignorant" classifier trained on the whole stream of reviews, the other one consisting of one "entity-centric" classifier per entity. We show that the entity-ignorant classifier contributes most for entities with very few reviews, i.e. during the cold-start, while the entity-centric classifiers contribute most after acquiring enough information on the corresponding entities. We study our approach on a stream of product reviews, show that our ensemble improves the performance of its members, and we discuss the conditions under which one member contributes more than the other.

@inproceedings{noauthororeditor, abstract = {Opinion stream classification algorithms adapt the model to the arriving review texts and, depending on the forgetting scheme, reduce the contribution old reviews have upon the model. Reviews are assumed independent, and information on the entity to which a review refers, i.e. to the opinion target, is thereby ignored. This implies that the prediction of a review's label is based more on reviews referring to other, more popular or simply more recently inspected entities, while reviews referring to the same entity might be ignored as too old. In this study, we enforce that the reviews to each entity are taken into account for learning, adaption and forgetting. We split the original stream to substreams, each substream comprised by the reviews referring to the same entity (opinion target). This allows us to deal with differences in the speed of each sub-stream and to exploit the impact of the entity itself on the labels of the reviews referring to it. For this constellation of substreams we propose a pair of two voting classifiers, one being the global, "entity-ignorant" classifier trained on the whole stream of reviews, the other one consisting of one "entity-centric" classifier per entity. We show that the entity-ignorant classifier contributes most for entities with very few reviews, i.e. during the cold-start, while the entity-centric classifiers contribute most after acquiring enough information on the corresponding entities. We study our approach on a stream of product reviews, show that our ensemble improves the performance of its members, and we discuss the conditions under which one member contributes more than the other.}, added-at = {2020-01-13T09:56:07.000+0100}, author = {Beyer, Christian and Unnikrishnan, Vishnu and Niemann, Uli and Matuszyk, Pawel and Ntoutsi, Eirini and Spiliopoulou, Myra}, biburl = {https://www.bibsonomy.org/bibtex/2942c1ca021f2fba5a59b3a0e8d17b2fb/kmd-ovgu}, booktitle = {Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing}, doi = {https://doi.org/10.1145/3297280.3297333}, interhash = {b8d6807e34995aa442e7f0e22a088d38}, intrahash = {942c1ca021f2fba5a59b3a0e8d17b2fb}, keywords = {entity-centric-learning kmd stream-mining}, pages = {564-573}, publisher = {ACM}, timestamp = {2020-01-13T10:09:20.000+0100}, title = {Exploiting Entity Information for Stream Classification over a Stream of Reviews}, url = {https://doi.org/10.1145/3297280.3297333}, year = 2019 }