TY - GEN
T1 - Towards confidence in the truth
T2 - 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016
AU - Xiao, Houping
AU - Gao, Jing
AU - Li, Qi
AU - Ma, Fenglong
AU - Su, Lu
AU - Feng, Yunlong
AU - Zhang, Aidong
N1 - Publisher Copyright:
© 2016 ACM.
PY - 2016/8/13
Y1 - 2016/8/13
N2 - The demand for automatic extraction of true information (i.e., truths) from conflicting multi-source data has soared recently. A variety of truth discovery methods have witnessed great successes via jointly estimating source reliability and truths. All existing truth discovery methods focus on providing a point estimator for each object's truth, but in many real-world applications, confidence interval estimation of truths is more desirable, since confidence interval contains richer information. To address this challenge, in this paper, we propose a novel truth discovery method (ETCIBoot) to construct confidence interval estimates as well as identify truths, where the bootstrapping techniques are nicely integrated into the truth discovery procedure. Due to the properties of bootstrapping, the estimators obtained by ETCIBoot are more accurate and robust compared with the state-of-the-art truth discovery approaches. Theoretically, we prove the asymptotical consistency of the confidence interval obtained by ETCIBoot . Experimentally, we demonstrate that ETCIBoot is not only effective in constructing confidence intervals but also able to obtain better truth estimates.
AB - The demand for automatic extraction of true information (i.e., truths) from conflicting multi-source data has soared recently. A variety of truth discovery methods have witnessed great successes via jointly estimating source reliability and truths. All existing truth discovery methods focus on providing a point estimator for each object's truth, but in many real-world applications, confidence interval estimation of truths is more desirable, since confidence interval contains richer information. To address this challenge, in this paper, we propose a novel truth discovery method (ETCIBoot) to construct confidence interval estimates as well as identify truths, where the bootstrapping techniques are nicely integrated into the truth discovery procedure. Due to the properties of bootstrapping, the estimators obtained by ETCIBoot are more accurate and robust compared with the state-of-the-art truth discovery approaches. Theoretically, we prove the asymptotical consistency of the confidence interval obtained by ETCIBoot . Experimentally, we demonstrate that ETCIBoot is not only effective in constructing confidence intervals but also able to obtain better truth estimates.
UR - http://www.scopus.com/inward/record.url?scp=84984984328&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84984984328&partnerID=8YFLogxK
U2 - 10.1145/2939672.2939831
DO - 10.1145/2939672.2939831
M3 - Conference contribution
AN - SCOPUS:84984984328
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 1935
EP - 1944
BT - KDD 2016 - Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
Y2 - 13 August 2016 through 17 August 2016
ER -