%0 Generic %1 sinha2018dawidskene %A Sinha, Vaibhav B %A Rao, Sukrut %A Balasubramanian, Vineeth N %D 2018 %K aggregation classification computing crowd crowdsourcing crowdworker expert human label sentiment social vote %T Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification %U http://arxiv.org/abs/1803.02781 %X Many real world problems can now be effectively solved using supervised machine learning. A major roadblock is often the lack of an adequate quantity of labeled data for training. A possible solution is to assign the task of labeling data to a crowd, and then infer the true label using aggregation methods. A well-known approach for aggregation is the Dawid-Skene (DS) algorithm, which is based on the principle of Expectation-Maximization (EM). We propose a new simple, yet effective, EM-based algorithm, which can be interpreted as a `hard' version of DS, that allows much faster convergence while maintaining similar accuracy in aggregation. We show the use of this algorithm as a quick and effective technique for online, real-time sentiment annotation. We also prove that our algorithm converges to the estimated labels at a linear rate. Our experiments on standard datasets show a significant speedup in time taken for aggregation - upto $\sim$8x over Dawid-Skene and $\sim$6x over other fast EM methods, at competitive accuracy performance. The code for the implementation of the algorithms can be found at https://github.com/GoodDeeds/Fast-Dawid-Skene

@misc{sinha2018dawidskene, abstract = {Many real world problems can now be effectively solved using supervised machine learning. A major roadblock is often the lack of an adequate quantity of labeled data for training. A possible solution is to assign the task of labeling data to a crowd, and then infer the true label using aggregation methods. A well-known approach for aggregation is the Dawid-Skene (DS) algorithm, which is based on the principle of Expectation-Maximization (EM). We propose a new simple, yet effective, EM-based algorithm, which can be interpreted as a `hard' version of DS, that allows much faster convergence while maintaining similar accuracy in aggregation. We show the use of this algorithm as a quick and effective technique for online, real-time sentiment annotation. We also prove that our algorithm converges to the estimated labels at a linear rate. Our experiments on standard datasets show a significant speedup in time taken for aggregation - upto $\sim$8x over Dawid-Skene and $\sim$6x over other fast EM methods, at competitive accuracy performance. The code for the implementation of the algorithms can be found at https://github.com/GoodDeeds/Fast-Dawid-Skene}, added-at = {2020-10-21T11:50:06.000+0200}, author = {Sinha, Vaibhav B and Rao, Sukrut and Balasubramanian, Vineeth N}, biburl = {https://www.bibsonomy.org/bibtex/28e672879b9c2f710c124699c4156b22e/jaeschke}, description = {[1803.02781] Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification}, interhash = {9bd6913521b6434d60b4320597da333b}, intrahash = {8e672879b9c2f710c124699c4156b22e}, keywords = {aggregation classification computing crowd crowdsourcing crowdworker expert human label sentiment social vote}, note = {cite arxiv:1803.02781Comment: 8 pages, 5 tables, 1 figure, KDD Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM) 2018}, timestamp = {2020-10-21T11:50:06.000+0200}, title = {Fast Dawid-Skene: A Fast Vote Aggregation Scheme for Sentiment Classification}, url = {http://arxiv.org/abs/1803.02781}, year = 2018 }