@inproceedings{9b4b085458814e70869ff32b79f65196,
title = "Ballpark learning: Estimating labels from rough group comparisons",
abstract = "We are interested in estimating individual labels given only coarse, aggregated signal over the data points. In our setting, we receive sets (“bags”) of unlabeled instances with constraints on label proportions. We relax the unrealistic assumption of known label proportions, made in previous work; instead, we assume only to have upper and lower bounds, and constraints on bag differences. We motivate the problem, propose an intuitive formulation and algorithm, and apply our methods to real world scenarios. Across several domains, we show how using only proportion constraints and no labeled examples, we can achieve surprisingly high accuracy. In particular, we demonstrate how to predict income level using rough stereotypes and how to perform sentiment analysis using very little information. We also apply our method to guide exploratory analysis, recovering geographical differences in twitter dialect.",
author = "Tom Hope and Dafna Shahaf",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG 2016.; 15th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2016 ; Conference date: 19-09-2016 Through 23-09-2016",
year = "2016",
doi = "https://doi.org/10.1007/978-3-319-46227-1_19",
language = "الإنجليزيّة",
isbn = "9783319462264",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "299--314",
editor = "Niels Landwehr and Jilles Giuseppe and Giuseppe Manco and Paolo Frasconi",
booktitle = "Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2016, Proceedings",
address = "ألمانيا",
}