《计算机应用研究》|Application Research of Computers

针对问答系统隐性垃圾内容的答案再排序模型

Re-ranking model for implicit spam answers in CQA

免费全文下载 (已被下载 次)  
获取PDF全文
作者 田雅,郑明春,乔鸿
机构 山东师范大学 管理科学与工程学院,济南 250014
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)08-2315-04
DOI 10.3969/j.issn.1001-3695.2017.08.018
摘要 社会化问答系统为人们提供知识共享的平台,然而网站上存在着诸如推广信息的隐性垃圾内容,这些内容在包含诸多有用内容的基础上含有虚假的推广信息,这些虚假信息可能会带来更严重的后果,因此,如何检测及识别这些隐性的垃圾内容尤为重要。通过在任务型的网上交易平台搜集实验数据,创新地提出了一种基于物理学牛顿第二运动定律的优化答案排序模型,旨在原有的答案序列的基础上,加入隐性垃圾内容的特征,通过将回答者提交的答案看成是受多个力作用的物体,答案的排序看成是物体的下落过程,来对答案进行重新排序,使虚假信息沉淀到答案序列下方。实验证明,此模型能够快速有效地完成对答案的排序,实现按照质量对答案进行排序。
关键词 问答系统;隐性垃圾内容;答案再排序模型
基金项目 国家自然科学基金资助项目(61402266)
国家社会科学基金资助项目(14BTQ049)
本文URL http://www.arocmag.com/article/01-2017-08-018.html
英文标题 Re-ranking model for implicit spam answers in CQA
作者英文名 Tian Ya, Zheng Mingchun, Qiao Hong
机构英文名 SchoolofManagementScience&Engineering,ShandongNormalUniversity,Jinan250014,China
英文摘要 Community question answering system provides a platform for people to share knowledge. However, there are some content like the promotion of information hidden in the answers. It may lead to serious consequences. Therefore, how to detect and identify this hidden spam is particularly important. By collecting experimental data on a task-based online trading platform, this paper proposed an optimization model for re-ranking answers using physics of Newton’s second law innovatively. Each answer was seen as a falling object with several forces. And the answers would be rearranged, letting the spam information to the bottom of the answer sequence. Experiments show that this model can be completed quickly and efficiently in re-ranking the answer sequence.
英文关键词 CQA; implicit spam answers; re-ranking model
参考文献 查看稿件参考文献
  [1] Wang Xinjing, Tu Xudong, Feng Dan, et al. Ranking community answers by modeling question-answer relationships via analogical reaso-ning[C] //Proc of the 32nd Annual International ACM SIGIR Confe-rence on Research and Development in Information Retrieval. 2009:179-186.
[2] Kim S, Oh J S, Oh S. Best-answer selection criteria in a social Q&A site from the user-oriented relevance perspective[C] //Proc of the 70th Annual Meeting of American Society for Information Science and Technology. 2007:1-15.
[3] Kim S, Oh S. Users’ relevance criteria for evaluating answers in a social Q&A site[J] . Journal of the American Society for Information Science and Technology, 2009, 60(4):716-727.
[4] Zhu Zhemin, Bernhard D, Gurevych I. A multi-dimensional model for assessing the quality of answers in social Q&A[EB/OL] . [2014-01-20] . http://tuprints. ulb. tu-darmstadt. de/ 1940/1/TR_dimension_model. pdf.
[5] Ishikawa D, Kando N, Sakai T. What makes a good answer in community question answering? An analysis of assessors’ criteria[C] //Proc of the 4th International Workshop on Evaluating Information Access. 2011.
[6] 蒋楠, 王鹏程. 社会化问答服务中用户需求与信息内容的相关性评价研究——以“百度知道”为例[J] . 信息资源管理学报, 2012, 2(3):35-45.
[7] Yan Zhenlei, Zhou Jie. Optimal answerer ranking for new questions in community question answering[J] . Information Processing and Management, 2015, 51(1):163-178.
[8] Ko J, Luo Si, Nyberg E. Combining evidence with a probabilistic framework for answer ranking and answer merging in question answe-ring[J] . Information Processing & Management, 2010, 46(5):541-554.
[9] Yen S J, Wu Y C , Yang Jiechi, et al. A support vector machine-based context-ranking model for question answering[J] . Information Sciences, 2013, 224(2):77-87.
[10] Wei Wei, Ming Zhaoyan, Nie Liqiang, et al. Exploring heterogeneous features for query-focused summarization of categorized community answers[J] . Information Sciences, 2016, 330:403-423.
[11] Ntalianis K, Salem A B M, Emary L E. Social media content ranking based on social computing and user influence[C] //Proc of International Conference on Communication, Management and Information Technology. 2015.
[12] Moschitti A, Quarteroni S. Linguistic kernels for answer re-ranking in question answering systems[J] . Information Processing & Ma-nagement, 2011, 47(6):825-842.
[13] Li Chengkai. On contextual ranking queries in databases[J] . Information Systems, 2013, 38(4):509-523.
[14] Atkinson J, Figueroa A, Andrade C. Evolutionary optimization for ranking how-to questions based on user-generated contents[J] . Expert Systems with Applications, 2013, 40(17):7060-7068.
[15] Wu Y C, Yang Jiechi, Lee Y S. A weighted string pattern matching-based passage ranking algorithm for video question answering[J] . Expert Systems with Applications, 2008, 34(4):2588-2600. [16] Han K S, Song Y I, Kim S B, et al. Answer extraction and ranking strategies for definitional question answering using linguistic features and definition terminology[J] . Information Processing & Management, 2007, 43(2) :353-364.
[17] Figueroa A, Neumann G. Category-specific models for ranking effective paraphrases in community question answering[J] . Expert Systems with Applications, 2014, 41(10):4730-4742.
[18] Fukumoto J, Aburai N, Yamanishi R. Interactive document expansion for answer extraction of question answering system[C] //Proc of the 17th International Conference on Knowledge Based and Intelligent Information and Engineering Systems. 2013.
[19] Surdeanu M, Ciaramita M, Zaragoza H. Learning to rank answers to non-factoid questions from Web collections[J] . Computational Linguistics, 2011, 37(2):351-383.
[20] Hieber F, Riezler S. Improved answer ranking in social question-answering portals[C] //Proc of the 3rd International CIKM Workshop on Search and Mining User-Generated Contents. New York:ACM Press, 2011:19-26.
[21] 艾萨克·牛顿. 自然哲学的数学原理[M] . 王克迪, 译. 西安:陕西人民出版社, 2001.
[22] Feng Xiaonan, Wu Jinfu, Tian Ye. Community detection based on social network analysis in question and answer systems[J] . Journal of Computational Information Systems, 2013, 9(15):6297- 6305.
收稿日期 2016/6/6
修回日期 2016/7/20
页码 2315-2318,2371
中图分类号 TP391
文献标志码 A