کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
533804 870167 2015 6 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Predicting the quality of user-generated answers using co-training in community-based question answering portals
ترجمه فارسی عنوان
پیش بینی کیفیت پاسخ های تولید شده با استفاده از همکاری در سوال مبتنی بر جامعه در پاسخ به پورتال
کلمات کلیدی
همکاری آموزشی، روش نیمه نظارت، پاسخ کیفیت پیش بینی، ویژگی های زبان سطح ویژگی های اجتماعی
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی


• We improve the co-training method to predict the quality of answers.
• Two semi-supervised learning methods based on co-training are presented.
• Surface linguistic features and social features are proposed.

Predicting the quality of user-generated answers is definitely of great importance for community-based question answering (CQA) due to the frequent occurrence of low-quality answers. Most existing answer quality prediction works combine non-textual features of user-generated answers directly without considering the diversity of non-textual features. In this paper, we propose two co-training approaches: random subspace split-based co-training (RSS-CoT) and content and social split-based co-training (CS-CoT) to predict the quality of answers by mining the relationships of non-textual features and unlabeled data in CQA. Our results demonstrate that both appropriate combination of non-textual features and unlabeled data can promote the prediction performance of answer quality.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition Letters - Volume 58, 1 June 2015, Pages 29–34
نویسندگان
, , , , ,