论文部分内容阅读
【目的/意义】随着社交网络的普及与快速发展,人们越来越多地依赖于网络聊天工具进行交流,针对QQ群组聊天信息过载用户无法从聊天记录中快速获取所需信息的问题,本文开展了聊天热点主题提取和QQ群组用户聊天行为分析的研究。【方法/过程】采集了一个技术类QQ群的聊天数据,利用Gibbs算法和LDA模型提取群组聊天数据中的主题并对其进行分析。【结果/结论】发现群组的主题可以分为三类:技术类、生活类和综合类。其中,技术类话题讨论的高峰集中在工作时间,没有继承性;大家普遍关心生活类话题,该话题有继承性。由于群组聊天的即时性、交互性和网络领袖的影响,一个时间段内群中只有一个热点主题。该研究结果可为群组聊天行为和热点分析提供参考。
[Purpose / Significance] With the popularization and rapid development of social networks, people rely more and more on network chatting tools for communication. In view of the problem that users in QQ group chatting information overload can not obtain required information quickly from chatting records, This article has carried on the research of chat hot topic extraction and QQ group user chat behavior analysis. [Method / Procedure] The chat data of a technical QQ group was collected, and the topics in the group chat data were extracted and analyzed by using the Gibbs algorithm and the LDA model. [Results / Conclusion] The topics found in the group can be divided into three categories: technical category, living category and comprehensive category. Among them, the topic of technical topics is concentrated in the peak hours of work, there is no inheritance; people are generally concerned about the topic of life, the topic has inheritance. Because of the immediacy, interactivity, and network leadership of group chat, there is only one hot topic in a group in a time period. The results of this study provide a reference for group chatting behavior and hot spot analysis.