基于文本在线聊天中非语言行为线索的识别、提取与统计分析  

Identification,extraction and statistical analysis of non-verbal behavioral cues in text-based online chat

作　　者：刘浪沙 LIU Langsha(Guizhou Communications Polytechnic,Guiyang 551400,China)

机构地区：[1]贵州交通职业技术学院,贵州贵阳551400

出　　处：《贵州科学》2024年第3期90-96,共7页Guizhou Science

摘　　要：目的:旨在探讨基于文本的在线聊天中不同性别和不同角色之间是否存在非语言线索的使用差异,并找出可作为性别和角色识别指标的非语言线索。方法:首先对30对受试者之间产生的文本聊天数据中的非语言线索进行识别和提取;再对不同类型的线索,分别进行卡方检验和学生T检验。结果:有5种线索在不同性别间存在显著差异,有4种线索在不同角色间存在显著差异。该研究结果对电子商务等领域智能客服的研发、用户行为习惯的分析具有一定价值。This article aims to explore the differences in the use of non-verbal cues between different genders and roles in text-based online chat,and to identify non-verbal cues that can be used as indicators for gender and role recognition.Firstly,non-verbal cues in the text chat data generated between 30 pairs of subjects were identified and extracted.Then,chi-square test and student t-test were conducted on different types of cues.The results showed that there were significant statistical differences in five types of cues between different genders,and four types of cues between different roles.The findings of this study have important value for the development of intelligent customer service in e-commerce and the analysis of user behavior habits.

关 键 词：文本分析 自然语言处理 在线聊天 非语言行为线索 卡方检验 学生T检验 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]