基于依存句法分析的智能人机交互产品用户体验研究  

User Experience of Intelligent Human-Computer Interaction Products Based on Dependency Parsing

作　　者：谢雪梅[1] 王明慧 XIE XueMei;WANG MingHui(School of Economics and Management,Beijing University of Posts and Telecommunications,Beijing 100876,P.R.China)

机构地区：[1]北京邮电大学经济管理学院,北京100876

出　　处：《数字图书馆论坛》2024年第6期44-53,共10页Digital Library Forum

基　　金：北京邮电大学经济管理学院教学名师培育计划项目“教学名师培育建设”(编号:202306)资助。

摘　　要：智能人机交互产品因其交互自然化而备受关注,其用户体验研究尤为重要。现有对该类产品的用户体验研究聚焦于用户行为信息分析,而从在线评论中挖掘用户体验特征则是较新方向。基于依存句法分析和产品特征词库,通过人工设定提取规则从评论中提取产品特征和与之搭配的用户情感观点,并采用情感计算量化观点以获得用户体验特征。以智能屏产品为例展开研究,结果表明所提方法能解决产品特征和情感观点无法同步提取的问题,同时发现用户对产品的智能语音交互具有较高偏好程度,而对智能功能则满意度不足。根据结果针对产品的智能系统、外观及硬件配置等提出优化设计建议。Intelligent human-computer interaction products have attracted much attention due to their natural interaction,and the research on their user experience is particularly important.The existing research on the user experience of this type of products focuses on the analysis of user behavior information,while mining user experience characteristics from online reviews is a relatively new direction.Based on dependency parsing and the product feature thesaurus,this paper extracts product features and the corresponding user emotional opinions from the online reviews through artificially setting extraction rules,and adopts emotional computing to quantify the opinions to obtain user experience characteristics.Taking the intelligent screen products as an example to conduct the research,the results show that the method proposed can solve the problem that the product features and emotional opinions cannot be extracted simultaneously.At the same time,the study finds that users have a relatively high preference for the intelligent voice interaction of the product,but are not satisfied with the intelligent functions.Based on the results,optimization design suggestions are proposed for the intelligent system,appearance,and hardware configuration of the product.

关 键 词：智能人机交互产品 用户体验 依存句法分析 产品特征 情感计算 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]