Integrating rich user feedback into intelligent user interfaces Export

@inproceedings{citeulike:3089091, abstract = {The potential for machine learning systems to improve via a mutually beneficial exchange of information with users has yet to be explored in much detail. Previously, we found that users were willing to provide a generous amount of rich feedback to machine learning systems, and that the types of some of this rich feedback seem promising for assimilation by machine learning algorithms. Following up on those findings, we ran an experiment to assess the viability of incorporating real-time keyword-based feedback in initial training phases when data is limited. We found that rich feedback improved accuracy but an initial unstable period often caused large fluctuations in classifier behavior. Participants were able to give feedback by relying heavily on system communication in order to respond to changes. The results show that in order to benefit from the user's knowledge, machine learning systems must be able to absorb keyword-based rich feedback in a graceful manner and provide clear explanations of their predictions.}, address = {New York, NY, USA}, author = {Stumpf, Simone and Sullivan, Erin and Fitzhenry, Erin and Oberst, Ian and Wong, Weng-Keen and Burnett, Margaret}, booktitle = {IUI '08: Proceedings of the 13th international conference on Intelligent user interfaces}, citeulike-article-id = {3089091}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1378773.1378781}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1378773.1378781}, doi = {10.1145/1378773.1378781}, isbn = {9781595939876}, keywords = {active-annotation, intelligent-systems, interfaces, machine\_learning}, location = {Gran Canaria, Spain}, pages = {50--59}, posted-at = {2008-08-20 18:50:20}, priority = {3}, publisher = {ACM}, title = {Integrating rich user feedback into intelligent user interfaces}, url = {http://dx.doi.org/10.1145/1378773.1378781}, year = {2008} }

TY - CONF ID - citeulike:3089091 L3 - citeulike-article-id:3089091 N2 - The potential for machine learning systems to improve via a mutually beneficial exchange of information with users has yet to be explored in much detail. Previously, we found that users were willing to provide a generous amount of rich feedback to machine learning systems, and that the types of some of this rich feedback seem promising for assimilation by machine learning algorithms. Following up on those findings, we ran an experiment to assess the viability of incorporating real-time keyword-based feedback in initial training phases when data is limited. We found that rich feedback improved accuracy but an initial unstable period often caused large fluctuations in classifier behavior. Participants were able to give feedback by relying heavily on system communication in order to respond to changes. The results show that in order to benefit from the user's knowledge, machine learning systems must be able to absorb keyword-based rich feedback in a graceful manner and provide clear explanations of their predictions. CY - Gran Canaria, Spain SN - 9781595939876 AD - New York, NY, USA EP - 59 TI - Integrating rich user feedback into intelligent user interfaces PB - ACM T2 - IUI '08: Proceedings of the 13th international conference on Intelligent user interfaces SP - 50 KW - active-annotation KW - intelligent-systems KW - interfaces KW - machine_learning AU - Stumpf, Simone AU - Sullivan, Erin AU - Fitzhenry, Erin AU - Oberst, Ian AU - Wong, Weng-Keen AU - Burnett, Margaret PY - 2008/// UR - http://dx.doi.org/10.1145/1378773.1378781 ER -