Purpose

This study aims to both identify content-based and interaction-based online consumer complaint types and predict complaint types according to the complaint magnitude rooted in complainants' personality traits, emotion, Twitter usage activity, as well as complaint's sentiment polarity, and interaction rate.

Design/methodology/approach

In total, 297,000 complaint tweets were collected from Twitter, featuring over 220,000 consumer profiles and over 24 million user tweets. The obtained data were analyzed via two-step machine learning approach.

Findings

This study proposes a set of content and profile features that can be employed for determining complaint types and reveals the relationship between content features, profile features and online complaint type.

Originality/value

This study proposes a novel model for identifying types of online complaints, offering a set of content and profile features that can be used for predicting complaint type, and therefore introduces a flexible approach for enhancing online complaint management.

中文翻译：

---

在线投诉处理：基于文本分析的分类框架

目的

本研究旨在识别基于内容和基于交互的在线消费者投诉类型，并根据投诉者的性格特征、情绪、Twitter 使用活动以及投诉的情绪极性和互动率所产生的投诉程度来预测投诉类型。

设计/方法论/途径

Twitter 总共收集了 297,000 条投诉推文，包含超过 220,000 条消费者档案和超过 2400 万条用户推文。通过两步机器学习方法对获得的数据进行分析。

发现

本研究提出了一组可用于确定投诉类型的内容和个人资料特征，并揭示了内容特征、个人资料特征和在线投诉类型之间的关系。

原创性/价值

本研究提出了一种识别在线投诉类型的新颖模型，提供了一组可用于预测投诉类型的内容和个人资料特征，因此引入了一种增强在线投诉管理的灵活方法。