Measuring e-Commerce service quality from online customer review using sentiment analysis
Measuring e-Commerce service quality from online customer review using sentiment analysis
复制标题
DOI：
10.1088/1742-6596/971/1/012053
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
P. Sari;A. Alamsyah;Sulistyo Wibowo
中科院分区：
文献类型：
--
作者：
P. Sari;A. Alamsyah;Sulistyo Wibowo
电子商贸了解市场的最大挑战，是如何根据顾客的感受，绘制服务质素的图表。通过在线用户评论收集用户感知的机会被认为是比直接抽样方法更快的方法。为了了解服务质量水平，采用情感分析方法，将电子服务质量（e-Servqual）的五个维度的评论分为正面和负面情绪。作为本研究的案例研究，我们使用印度尼西亚最大的电子商务服务之一Tokopedia。我们在几个月的观察中获得了对Tokopedia服务质量的在线评论意见。由于Naïve贝叶斯分类方法准确率高，支持大数据处理，因此采用该分类方法。结果表明，由于负面情绪较高，个性化和可靠性维度需要更多的关注。同时，信任度和网页设计维度都有很高的积极情绪，这意味着它有很好的服务。反应性维度具有积极情绪和消极情绪的平衡。
The biggest e-Commerce challenge to understand their market is to chart their level of service quality according to customer perception. The opportunities to collect user perception through online user review is considered faster methodology than conducting direct sampling methodology. To understand the service quality level, sentiment analysis methodology is used to classify the reviews into positive and negative sentiment for five dimensions of electronic service quality (e-Servqual). As case study in this research, we use Tokopedia, one of the biggest e-Commerce service in Indonesia. We obtain the online review comments about Tokopedia service quality during several month observations. The Naïve Bayes classification methodology is applied for the reason of its high-level accuracy and support large data processing. The result revealed that personalization and reliability dimension required more attention because have high negative sentiment. Meanwhile, trust and web design dimension have high positive sentiments that means it has very good services. The responsiveness dimension have balance sentiment positive and negative.