基于人类动力学的社会化问答社区优秀贡献者行为研究——以“知乎”为例
|
摘要
【目的/意义】社会化问答社区中的优秀贡献者能够经常性地提供优质的回答内容,对社区回答内容质量的提升起到了关键的作用,因此,对社区中优秀贡献者行为进行研究具有重要意义。【方法/过程】以"知乎"社区为例,通过爬虫采集社区上"优秀回答者"问题回答相关的行为数据,综合运用人类动力学的理论及相关的统计分析方法对采集到的行为数据进行分析和仿真验证。【结果/结论】"优秀回答者"回答问题的行为不是一个随机事件,而是一个时间间隔分布满足胖尾特征的幂律分布;其他用户对回答内容的点赞会对"优秀回答者"回答问题的兴趣产生更大的激励影响,进而可以减小"优秀回答者"连续两次回答问题的时间间隔;基于兴趣的人类动力学模型可以很好地解释"优秀回答者"回答问题的行为特征。
【Purpose/significance】The outstanding contributors in a social Q&A community can often provide high quality answers and play a key role in improving the quality of answers in the community. Therefore, it is of great significance to study the behavior of the outstanding contributors in the social Q&A community.【Method/process】Taking the "Zhihu" community as an example, this research collects the answering-relevant behavior data of "excellent responders" and makes a comprehensive use of human dynamics theory and the related statistical analysis methods to analyze and verify the behavior data.【Result/conclusion】The answering behavior of "excellent responders" is not a random event, but a power law distribution of the interval time of answering which satisfies the fat tail characteristic. The other users' "Likes" on the answer content will have a greater incentive effect on the answering interest of the "excellent responder" and then reduce the interval time of answering. The interest-driven human dynamics model can well explain the characteristics of answering behavior of the "excellent responder".
【Purpose/significance】The outstanding contributors in a social Q&A community can often provide high quality answers and play a key role in improving the quality of answers in the community. Therefore, it is of great significance to study the behavior of the outstanding contributors in the social Q&A community.【Method/process】Taking the "Zhihu" community as an example, this research collects the answering-relevant behavior data of "excellent responders" and makes a comprehensive use of human dynamics theory and the related statistical analysis methods to analyze and verify the behavior data.【Result/conclusion】The answering behavior of "excellent responders" is not a random event, but a power law distribution of the interval time of answering which satisfies the fat tail characteristic. The other users' "Likes" on the answer content will have a greater incentive effect on the answering interest of the "excellent responder" and then reduce the interval time of answering. The interest-driven human dynamics model can well explain the characteristics of answering behavior of the "excellent responder".
引文
1沈波,赖园园.网络问答社区“Quora”与“知乎”的比较分析[J].管理学刊,2016,29(5):43-50.
2蔡志斌.知乎社区成员互动关系研究--以“小米手机”话题为例[J].图书情报工作,2016,(17):88-93.
3刘佩,林如鹏.网络问答社区“知乎”的知识分享与传播行为研究[J].图书情报知识,2015,(6):109-119.
4 Yang L,Amatriain X.Recommending the world's knowledge:application of recommender systems at Quora[C]//Proceedings of the 10th ACM Conference on Recommender Systems.Boston,2016:389-389.
5 Paul S A,Hong L,Chi E H.Who is authoritative?understanding reputation mechanisms in Quora[C].Proceedings of Collective Intelligence,2012.
6 Maity S K,Sahni J S S,Mukherjee A.Analysis and prediction of question topic popularity in community Q&A sites:a case study of Quora[C]//Proceedings of the 9th International AAAI Conference on Web and Social Media.Palo Alto:AAAI Press,2015:238-247.
7 Oh S.The characteristics and motivations of health answerers for sharing information,knowledge,and experiences in online environments[J].Journal of the Association for Information Science and Technology,2012,63(3):543-557.
8 Choi E,Shah C.User motivations for asking questions in online Q&A services[J].Journal of the Association for Information Science and Technology,2016,67(5):1182-1197.
9 Jin J,Li Y,Zhong X,et al.Why users contribute knowledge to online communities:an empirical study of an online social Q&A community[J].Information&Management,2015,52(7):840-849.
10 Patil S,Lee K.Detecting experts on Quora:by their activity,quality of answers,linguistic characteristics and tempora behaviors[J].Social Network Analysis and Mining,2016,6(1):5.
11陈静.知乎用户网络与意见领袖在舆情传播中的作用[J].新闻研究导刊,2017,8(8):66-67.
12王秀丽.网络社区意见领袖影响机制研究--以社会化问答社区“知乎”为例[J].国际新闻界,2014,36(9):47-57.
13 Barabási A L.The origin of bursts and heavy tails in human dynamics[J].Nature,2005,435(7039):207.
14 Vázquez A,Oliveira J G,Dezs?Z,et al.Modeling bursts and heavy tails in human dynamics[J].Physical Review E2006,73(3):036127.
15焦玉,刘衍珩,王健,等.基于习惯的人类动力学建模[J].科学通报,2010,55(11):1070-1076.
16 Vázquez A.Impact of memory on human dynamics[J]Physica A:Statistical Mechanics and Its Applications,2006(373):747-752.
17 Wang C,Guan X,Qin T,et al.Modeling the heterogeneity of human dynamics based on the measurements of influential users in Sina Microblog[J].Physica A:Statistical Mechanics and Its Applications,2015,(428):239-249.
18 Yan D C,Wei Z W,Han X P,et al.Empirical analysis on the human dynamics of blogging behavior on Git Hub[J]Physica A:Statistical Mechanics&Its Applications,2017(465):775-781.
19 Han X P,Zhou T,Wang B H.Modeling human dynamics with adaptive interest[J].New Journal of Physics,2008,10(7):073010.
20 Shang M S,Chen G X,Dai S X,et al.Interest-driven model for human dynamics[J].Chinese Physics Letters2010,27(4):48701.
21 Yan Q,Yi L,Wu L.Human dynamic model co-driven by interest and social identity in the Micro Blog community[J]Physica A:Statistical Mechanics&Its Applications,2012391(4):1540-1545.
22周沧琦,赵千川,卢文博.基于兴趣变化的微博用户转发行为建模[J].清华大学学报:自然科学版,2015,55(11)1163-1170.
23冷建飞,高旭,朱嘉平.多元线性回归统计预测模型的应用[J].统计与决策,2016,(7):82-85.
24戴双星,陈冠雄,周涛,等.兴趣驱动的人类动力学模型研究[M].上海:上海系统科学出版社,2008:54-58.
2蔡志斌.知乎社区成员互动关系研究--以“小米手机”话题为例[J].图书情报工作,2016,(17):88-93.
3刘佩,林如鹏.网络问答社区“知乎”的知识分享与传播行为研究[J].图书情报知识,2015,(6):109-119.
4 Yang L,Amatriain X.Recommending the world's knowledge:application of recommender systems at Quora[C]//Proceedings of the 10th ACM Conference on Recommender Systems.Boston,2016:389-389.
5 Paul S A,Hong L,Chi E H.Who is authoritative?understanding reputation mechanisms in Quora[C].Proceedings of Collective Intelligence,2012.
6 Maity S K,Sahni J S S,Mukherjee A.Analysis and prediction of question topic popularity in community Q&A sites:a case study of Quora[C]//Proceedings of the 9th International AAAI Conference on Web and Social Media.Palo Alto:AAAI Press,2015:238-247.
7 Oh S.The characteristics and motivations of health answerers for sharing information,knowledge,and experiences in online environments[J].Journal of the Association for Information Science and Technology,2012,63(3):543-557.
8 Choi E,Shah C.User motivations for asking questions in online Q&A services[J].Journal of the Association for Information Science and Technology,2016,67(5):1182-1197.
9 Jin J,Li Y,Zhong X,et al.Why users contribute knowledge to online communities:an empirical study of an online social Q&A community[J].Information&Management,2015,52(7):840-849.
10 Patil S,Lee K.Detecting experts on Quora:by their activity,quality of answers,linguistic characteristics and tempora behaviors[J].Social Network Analysis and Mining,2016,6(1):5.
11陈静.知乎用户网络与意见领袖在舆情传播中的作用[J].新闻研究导刊,2017,8(8):66-67.
12王秀丽.网络社区意见领袖影响机制研究--以社会化问答社区“知乎”为例[J].国际新闻界,2014,36(9):47-57.
13 Barabási A L.The origin of bursts and heavy tails in human dynamics[J].Nature,2005,435(7039):207.
14 Vázquez A,Oliveira J G,Dezs?Z,et al.Modeling bursts and heavy tails in human dynamics[J].Physical Review E2006,73(3):036127.
15焦玉,刘衍珩,王健,等.基于习惯的人类动力学建模[J].科学通报,2010,55(11):1070-1076.
16 Vázquez A.Impact of memory on human dynamics[J]Physica A:Statistical Mechanics and Its Applications,2006(373):747-752.
17 Wang C,Guan X,Qin T,et al.Modeling the heterogeneity of human dynamics based on the measurements of influential users in Sina Microblog[J].Physica A:Statistical Mechanics and Its Applications,2015,(428):239-249.
18 Yan D C,Wei Z W,Han X P,et al.Empirical analysis on the human dynamics of blogging behavior on Git Hub[J]Physica A:Statistical Mechanics&Its Applications,2017(465):775-781.
19 Han X P,Zhou T,Wang B H.Modeling human dynamics with adaptive interest[J].New Journal of Physics,2008,10(7):073010.
20 Shang M S,Chen G X,Dai S X,et al.Interest-driven model for human dynamics[J].Chinese Physics Letters2010,27(4):48701.
21 Yan Q,Yi L,Wu L.Human dynamic model co-driven by interest and social identity in the Micro Blog community[J]Physica A:Statistical Mechanics&Its Applications,2012391(4):1540-1545.
22周沧琦,赵千川,卢文博.基于兴趣变化的微博用户转发行为建模[J].清华大学学报:自然科学版,2015,55(11)1163-1170.
23冷建飞,高旭,朱嘉平.多元线性回归统计预测模型的应用[J].统计与决策,2016,(7):82-85.
24戴双星,陈冠雄,周涛,等.兴趣驱动的人类动力学模型研究[M].上海:上海系统科学出版社,2008:54-58.