In this work, we present a method for classifying the quality of blog comments using Linear-Chain Conditional Random Fields (CRFs). This approach is found to yield high accuracy on binary classification of high-quality comments, with conversational features contributing strongly to the accuracy. We also present a new corpus of blog data in conversational form, complete with user-generated quality moderation labels from the science and technology news blog Slashdot.

@inproceedings{fitzgerald-carenini-murray-joty-cai-11, abstract = {In this work, we present a method for classifying the quality of blog comments using Linear-Chain Conditional Random Fields (CRFs). This approach is found to yield high accuracy on binary classification of high-quality comments, with conversational features contributing strongly to the accuracy. We also present a new corpus of blog data in conversational form, complete with user-generated quality moderation labels from the science and technology news blog Slashdot.}, address = {St. John's, Canada}, author = {Nicholas FitzGerald and Giuseppe Carenini and Gabriel Murray and Shafiq Joty}, booktitle = {Advances in Artificial Intelligence - 24th Canadian Conference on Artificial Intelligence Proceedings}, doi = {10.1007/978-3-642-21043-3_15}, pages = {122--127}, series = {CAI'11}, title = {Exploiting Conversational Features to Detect High-Quality Blog Comments}, url = {https://doi.org/10.1007/978-3-642-21043-3_15}, year = {2011} }