Learning to Perform Moderation in Online Forums
Shlomo Zilberstein, PI
Research Assistants: Andrew Arnt, Marek Petrik, Martin Allen
Online discussion forums facilitate group communication on the Internet.
Several types of discussions forums are used widely such as
mailing lists, newsgroups, or web-based bulletin boards. Such forums
provide a valuable resource for people looking to find
information, discuss ideas, and get advice on the Internet. The number of
forums continues to grow rapidly, covering such topics as politics,
technical news and advice, medical issues, and product ratings and
opinions. Unfortunately, many forums have too much activity, resulting in
information overload. Moderation systems are implemented in some forums as
a way to handle this problem, but due to sparsity issues, they are often
not sufficient. This project is aimed at automating the moderation
process, which currently relies entirely on humans. A framework for
learning to perform machine moderation is developed by finding patterns in
the moderations made by humans. Three fundamental research challenges are
addressed:
- Identify features that define a good or bad comment and
develop methods to extract these features efficiently.
- Develop classifiers that can be trained to moderate arbitrary
comments with high accuracy. Address the computational complexity of
the classifiers and develop techniques to improve their real-time
performance.
- Use the knowledge acquired in training on moderated forums in
different, possibly unmoderated, forums.
Millions of people already use
online forums on a regular basis. This project produces technology
that will improve the quality of service provided to users of online forums
and reduce the cost of operation by reducing substantially the amount of
human moderation that is needed.
Related Publications
- Learning Parallel Portfolios of Algorithms.
M. Petrik and S. Zilberstein.
Annals of Mathematics and Artificial Intelligence, 48(1-2):85-106, 2006.
[abs]
[pdf]
- Anytime Coordination Using Separable Bilinear Programs.
M. Petrik and S. Zilberstein.
Proceedings of the Twenty-Second Conference on Artificial
Intelligence (AAAI), Vancouver, British Columbia, 2007.
[abs]
[pdf]
- Average-Reward Decentralized Markov Decision Processes.
M. Petrik and S. Zilberstein.
Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence (IJCAI), 1997-2002, Hyderabad, India, 2007.
[abs]
[pdf]
- Web Page Clustering using Heuristic Search in the Web Graph.
R. Bekkerman, S. Zilberstein, and J. Allan.
Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence (IJCAI), 2280-2285, Hyderabad, India, 2007.
[abs]
[pdf]
- Learning Static Parallel Portfolios of Algorithms.
M. Petrik and S. Zilberstein.
Proceedings of the Ninth International Symposium on Artificial
Intelligence and Mathematics (AI&MATH), Ft. Lauderdale, Florida, 2006.
[abs]
[pdf]
- Learning Policies for Sequential Time and Cost Sensitive Classification.
A. Arnt and S. Zilberstein.
KDD 2005 Workshop on Utility-Based Data Mining, Chicago, Illinois, 2005.
[abs]
[pdf]
- Generating Admissible Heuristics by Abstraction for Search in Stochastic Domains.
N. Beliaeva and S. Zilberstein.
Proceedings of the Symposium on Abstraction, Reformulation, and
Approximation (SARA), Airth Castle, Scotland, 2005.
[abs]
[pdf]
- Attribute Measurement Policies for Cost-Effective Classification.
A. Arnt and S. Zilberstein.
SIAM/SDM Workshop on Data Mining in Resource Constrained
Environments, Lake Buena Vista, Florida, 2004.
[abs]
[pdf]
- Attribute Measurement Policies for Cost-Effective Classification.
A. Arnt and S. Zilberstein.
Proceedings of the 4th IEEE International Conference on Data
Mining, Brighton, UK, 2004.
[abs]
[pdf]
- Learning to Perform Moderation in Online Forums.
A. Arnt and S. Zilberstein.
Proceedings of the IEEE/WIC International Conference on Web Intelligence,
Halifax, Canada, 2003.
[abs]
[pdf]
shlomo@cs.umass.edu