The value of а customer for the company is not measured only by the monetary effect, but also by the degree of its satisfaction. Satisfied customers spread positive word of mouth, while dissatisfied customers spread negative one (in online or offline environment). Their voice shapes company reputation and the reputation is one of the key parameters in choosing a product, service, or a company. In order to look into customer satisfaction, companies need to get certain feedback from consumers. The traditional way of collecting feedback from consumers is questionnaires. However, the way in which consumers express their opinions on social media opens up new opportunities and makes it easier for companies to cover a larger number of consumers, to collect data of interest and to continuously monitor the brand. Social media sites have significantly changed the nature of human activities, interactions and ways of disseminating information. Consumer behavior has changed accordingly. In search for information about products and services consumers are planning to buy or use, offline sources of information are increasingly replaced with online sources and e-WoM. Before making a purchase decision, consumers visit many sites and read the content and comments that other users have generated. Within these contents – texts that users voluntarily post on the Internet and make it publicly available – users freely express their views, opinions, describe their consumer experience, the problems they have encountered and the way in which the problems were addressed, they point to the aspects of products or services they are satisfied or dissatisfied with. These contents shape the opinions of future consumers in great extent and affect their consumer actions. Numerous studies have confirmed the impact these sources have on consumer behavior: • Consumers appreciate opinions of other individuals and trust them more than the company's promotional campaigns, • Consumers have equal trust in online comments and reviews as in personal recommendations from friends, • Online comments on products and services are on the third place according to the influence on buying decisions (after coupons and discounts). Each business can benefit from analysis of social media content since it comprises useful feedback from consumers in form of expressed opinions and attitudes. Opinions and attitudes are extremely subjective. Due to subjectivity it is necessary to analyze a collection of opinions of different people instead of a single opinion which expresses a subjective view of an individual. In addition to this large number of available sources, the amount of data makes it impossible to manually process them and identify the general pattern, problem or source of (dis)satisfaction. Hence, automated analysis of unstructured content from social media sites is required, i.e. the application of sentiment analysis or opinion mining. Sentiment analysis is a young research area which has rapidly developed during the past 10 years and it has achieved significant commercialization. The surrounding industries also experienced significant expansion. Sentiment analysis allows companies to analyze public opinion, attitudes and emotions directed at a particular entity (e.g. a particular person, a political candidate, a party, a law, a company, a specific product, or a product feature) which expresses particular sentiment or points to (usually positive, negative or neutral), as well as all variations and gradations of the sentiment. In addition to the significance of sentiment analysis for business, this paper deals with sentiment analysis process and underlying data mining techniques.

中文翻译：

---

客户数据的情感分析

客户对公司的价值不仅取决于货币效应，还取决于其满意度。满意的客户会传播正面的口碑，而不满意的客户会传播负面的口碑（在线或离线环境中）。他们的声音影响着公司的声誉，声誉是选择产品，服务或公司的关键参数之一。为了调查客户满意度，公司需要从消费者那里获得某些反馈。从消费者那里收集反馈的传统方式是问卷。然而，消费者在社交媒体上表达意见的方式带来了新的机会，并使公司更容易覆盖更多的消费者，收集感兴趣的数据并持续监控品牌。社交媒体网站已大大改变了人类活动，互动和信息传播方式的性质。消费者行为发生了相应的变化。在搜索有关消费者计划购买或使用的产品和服务的信息时，离线信息源越来越多地被在线资源和e-WoM取代。在做出购买决定之前，消费者会访问许多站点并阅读其他用户生成的内容和评论。在这些内容（用户自愿在Internet上发布并公开发布的文本）中，用户自由表达他们的观点，意见，描述他们的消费者体验，遇到的问题以及解决问题的方式，他们指出产品或服务的各个方面，它们会感到满意或不满意。这些内容在很大程度上塑造了未来消费者的意见，并影响了他们的消费者行为。大量研究证实了这些来源对消费者行为的影响：•消费者欣赏他人的意见，并比公司的促销活动更信任他们；•消费者对在线评论和评论的评价与对朋友的个人推荐同样信任，•在线评论根据对购买决定的影响（在优惠券和折扣之后），产品和服务的排名位于第三位。每个企业都可以从对社交媒体内容的分析中受益，因为它包括来自消费者的有用反馈，这些反馈以表达的观点和态度的形式。意见和态度非常主观。由于主观性，有必要分析不同人的意见的集合，而不是分析表示个人主观观点的单一意见。除了数量众多的可用来源外，大量的数据还使得无法手动处理它们并确定（不满意）总体模式，问题或来源。因此，需要对来自社交媒体站点的非结构化内容进行自动分析，即应用情感分析或观点挖掘。情感分析是一个年轻的研究领域，在过去的十年中发展迅速，并且已经实现了重要的商业化。周边行业也经历了显着的扩张。情感分析使公司能够分析针对特定实体的舆论，态度和情感（例如，表示特定情绪或指向（通常是正面，负面或中性）的所有特定人物，政治候选人，政党，法律，公司，特定产品或产品功能），以及情绪。除了情感分析对企业的意义外，本文还讨论了情感分析过程和基础数据挖掘技术。