Topics may Evolve: Using Complaint Data for Analysis

机译：主题可能会演变：使用投诉数据进行分析

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

User complaint data are quite valuable because they can reflect deficiencies of companies. Analyzing these short texts can help companies discover what topics users are complaining about. It is critical to locate and respond to these complaints timely so that companies can improve users' satisfaction and loyalty. As the data volume is large, topic model can help discover key complaint topics quickly. The complaint data are in the form of short texts and streams, traditional topic models like LDA and BTM are not suitable in this scenario, for the reason that LDA is designed for long texts and BTM can not handle streams. This paper firstly proposes an improved shorttext topic model called PMITI-BTM to generate topics from user complaint data statically, and then further extends this algorithm into a dynamic one to suit the streaming feature of data. To further analyze the topic evolution, we finally propose a clustering algorithm called TDWAP to acquire the evolution process of these topics in different time slices. For each algorithm, we do several experiments to prove its efficiency. Results show that our methods not only can improve the performance of short texts topic discovery, but also can discover the evolution of topics.

机译：用户投诉数据非常有价值，因为它们可以反映公司的缺陷。分析这些简短的文本可以帮助公司发现用户抱怨的主题。及时找到并响应这些投诉至关重要，这样公司才能提高用户的满意度和忠诚度。由于数据量很大，主题模型可以帮助快速发现关键的投诉主题。投诉数据采用短文本和流的形式，传统的主题模型（如LDA和BTM）不适用于这种情况，因为LDA是为长文本设计的，而BTM无法处理流。本文首先提出了一种改进的短文本主题模型，称为PMITI-BTM，可以从用户投诉数据中静态生成主题，然后将该算法进一步扩展为动态模型，以适应数据的流传输特征。为了进一步分析主题演变，我们最终提出了一种称为TDWAP的聚类算法，以获取这些主题在不同时间段内的演变过程。对于每种算法，我们进行了几次实验以证明其效率。结果表明，我们的方法不仅可以提高短文本主题发现的性能，而且可以发现主题的发展。

著录项

来源
《IEEE International Conference on Tools with Artificial Intelligence》|2017年|1296-1303|共8页
会议地点
作者
Lu-yao Xie; Lu-Xia Wang; Heng-Yang Lu; Ning Li; Chong-Jun Wangchj;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Clustering algorithms; Heuristic algorithms; Data models; Companies; Analytical models; Tools; Computational modeling;

机译：聚类算法;启发式算法;数据模型;公司;分析模型;工具;计算模型;

相似文献

外文文献
中文文献
专利

1. Understanding the topic evolution of scientific literatures like an evolving city: Using Google Word2Vec model and spatial autocorrelation analysis [J] . Hu Kai, Luo Qing, Qi Kunlun, Information Processing & Management . 2019,第4期

机译：了解像不断发展的城市这样的科学文献的主题演变：使用Google Word2Vec模型和空间自相关分析
2. Understanding the topic evolution of scientific literatures like an evolving city: Using Google Word2Vec model and spatial autocorrelation analysis [J] . Hu Kai, Luo Qing, Qi Kunlun, Information Processing & Management . 2019,第4期

机译：了解科学文献的主题演变，如不断发展的城市：使用Google Word2VEC模型和空间自相关分析
3. SIMULTANEOUS USE OF EVOLVING FACTOR ANALYSIS OF FLUORESCENCE SPECTRAL DATA AND ANALYSIS OF PH TITRATION DATA FOR COMPARISON OF THE ACID-BASE PROPERTIES OF FULVIC ACIDS [J] . Dasilva JCGE., Silva CSPCO., Machado AASC. Analytica chimica acta . 1996,第3期

机译：同时使用荧光光谱数据的演化因子分析和PH滴定数据的分析，以比较叶酸的酸碱性质
4. Topics may Evolve: Using Complaint Data for Analysis [C] . Lu-yao Xie, Lu-Xia Wang, Heng-Yang Lu, IEEE International Conference on Tools with Artificial Intelligence . 2017

机译：主题可能会发展：使用投诉数据进行分析
5. Two Topics in Data Analysis: Sample-based Optimal Transport and Analysis of Turbulent Spectra from Ship Track Data [D] . Kuang, Simeng Max. 2017

机译：数据分析中的两个主题：基于样本的最佳传输和来自船舶航迹数据的湍流光谱分析
6. Doctors experiences and their perception of the most stressful aspects of complaints processes in the UK: an analysis of qualitative survey data [O] . Tom Bourne, Joke Vanderhaegen, Renilt Vranken, 2016

机译：英国医生的经验及其对投诉过程最紧张方面的看法：定性调查数据分析
7. ABSTRACT Various body parts or organs can be analysed to identify the different diseases in the human body. Fingernail analysis is one of the ways to identify disease in the human body. Nails are the body part which are farthest from the heart and therefore receive oxygen at last. As a result the nails are the first who show the symptoms of a disease in the human body. Fingernails can be easily captured for diagnosis and there are no heavy equipment or no specific conditions required to use nail image for disease diagnosis, like in other tests and scanning processes. Human nails deliver beneficial information about complaints or any nutritive imbalances in the human body depending upon their shape, texture and colour. In human beings, numerous systemic and skin diseases can be easily analyzed through careful examination of nails of both the limbs. A lot of nail illnesses have been found to be primary signs of numerous underlying systemic illnesses. The colour, texture or shape changes in nails are signs of many diseases mainly affecting nails. Considering all these properties of nails a system is proposed that uses digital image processing (DIP) methods for identifying such changes in the human nail to get more precise results and predict numerous diseases effortlessly. With the emerging Internet of Things (IOT) concept the generated report is made available remotely, this will help users to reduce transportation efforts. As the system has to deal with large and private data, the security of data must be ensured. To keep the data confidential, the Blockchain concept which is one of the most emerging concepts in the field of data management is used. The paper contains the implementation of the digital image processing for feature extraction of nail images, usage of IOT (ThingSpeak cloud) for data storage and implementation of Blockchain to keep the system secured and theft free. KEY WORDS: Int ernet of thin gs (IOT), Image proc essin g, Thin gSpeak, RG B vavalues, Mean pi xel vavalues, Bloc kchain , Hash key. Disease Diagnostic System: Abnormalities in Human Nail [O] . Pranav S. Wazarkar 2020

机译：摘要的各个身体部位或器官可被分析以识别在人体内的不同的疾病。指甲分析来识别人体疾病的方法之一。指甲是身体一部分是离心脏最远，因此在最后接受氧气。作为结果，指甲是第一谁表现出人体疾病的症状。指甲可以容易地捕获用于诊断和没有重装或需要使用指甲图像用于疾病诊断，比如在其他测试和扫描过程没有特定的条件。人的指甲提供有关投诉或取决于它们的形状，纹理和色彩在人体内的任何营养失衡有益的信息。在人类中，许多全身性皮肤疾病是可以很容易地通过两个四肢指甲的仔细检查分析。很多指甲病已发现众多潜在系统性疾病的主要症状。在指甲的颜色，质地和形状的变化是许多疾病主要影响指甲的迹象。考虑到所有的指甲的这些性能的系统被提出，用于识别人指甲这样的变化以获得更精确的结果，并毫不费力预测许多疾病用途的数字图像处理（DIP）方法。随着物联网（IOT）的概念，新兴的互联网将生成的报告提供远程，这将帮助用户降低运输工作。由于系统必须处理大量的私人数据，数据的安全性必须得到保证。为了保持数据的机密性，使用Blockchain的概念，它是在数据管理领域的大多数新兴的概念之一。本文包含了数字图像处理的指甲图像，IOT（ThingSpeak云）的使用为数据存储和执行Blockchain的特征提取的执行，以保持固定的系统和盗窃免费。关键词：诠释薄GS（IOT），图像的ERNET PROC essin克，薄型gSpeak，RG乙vavalues，平均数PI XEL vavalues，阵营kchain，哈希密钥。疾病诊断系统：在人类指甲异常

Topics may Evolve: Using Complaint Data for Analysis

摘要

著录项

相似文献

相关主题

期刊订阅