面向中文APP用户评论数据的软件需求挖掘方法

Software Requirement Mining Method for Chinese APP User Review Data

从APP用户反馈数据中挖掘用户需求是APP迭代更新和需求获取的一种重要方式,用户在APP应用市场中发表对APP不同维度的评价,其中蕴含着用户对APP软件的改善需求。但是,目前用户反馈数据存在数量大、质量良莠不齐的状况,如何从海量的用户评论数据中省时省力地挖掘出有价值的需求,具有重要的研究与现实意义。文中着眼于APP开发问题,选取360手机助手中的APP用户评论数据,旨在挖掘蕴含于用户评论数据中的软件需求。首先,从功能性需求与非功能性需求两个维度出发,将APP用户评论数据中蕴含的软件需求划分为功能待添加、功能待改进、性能、可用性、可靠性5个需求类别;其次,对用户评论进行数据采集、标注,构建APP评论需求挖掘数据集;最后,利用构建好的数据集进行模型训练与交叉验证,探究主流深度学习方法相较于统计机器学习模型在该任务上的表现。实验表明,采用的深度学习模型TextCNN,TextRNN和Transformer相比传统的统计机器学习模型在此任务上更具优势。

Mining requirements from APP user review data is an important way to obtain requirements,because users publish reviews of different dimensions of APP in the APP application market,which contain many requirements for APP.The APP user review data on the 360 mobile assistant is chosen in our experiments,aiming to discover the software requirements contained in these review data.Firstly,the software requirements contained in APP user review data are divided into five categories,which include functions to be added,functions to be improved,performance,availability,and reliability.Secondly,data collection,labeling of user comments and constructing app review requirements mining data set are carried on.Finally,the constructed data set is used for model training and testing to explore the performance of deep learning methods compared with statistical machine lear-ning models on this task.The experiment results show that the deep learning models,TextCNN,TextRNN,and Transformer used in this paper,have more advantages in this task than traditional statistical machine learning models.