Sentiment analysis is a natural language processing task where the goal is to classify the sentiment polarity of the expressed opinions, although the aim to achieve the highest accuracy in sentiment classification for one particular language, does not truly reflect the needs of business. Sentiment analysis is often used by multinational companies operating on multiple markets. Such companies are interested in consumer opinions about their products and services in different countries (thus in different languages). However, most of the research in multi-language sentiment classification simply utilizes automated translation from minor languages to English (and then conducting sentiment analysis for English). This paper aims to contribute to the multi-language sentiment classification problem and proposes a language independent approach which could provide a good level of classification accuracy in multiple languages without using automated translations or language-dependent components (i.e. lexicons). The results indicate that the proposed approach could provide a high level of sentiment classification accuracy, even for multiple languages and without the language dependent components.
Expressing attitudes and opinions towards various entities (i.e. products, companies, people and events) has become pervasive with the recent proliferation of social media. Monitoring of what customers think is a key task for marketing research and opinion surveys, while measuring customers’ preferences or media monitoring have become a fundamental part of corporate activities. Most experiments on automated sentiment analysis focus on major languages (English, but also Chinese); minor or morphologically rich languages are addressed rather sparsely. Moreover, to improve the performance of machine-learning based classifiers, the models are often complemented with language-dependent components (i.e. sentiment lexicons). Such combined approaches provide a high level of accuracy but are limited to a single language or a single thematic domain.
This paper aims to contribute to this field and introduces an experiment utilizing a language– and domain– independent model for sentiment analysis. The model has been previously tested on multiple corpora, providing a trade-off between generality and the classification performance of the model. In this paper, we suggest a further extension of the model utilizing the surrounding context of the classified documents.
This chapter presents an extended study focused on application of automated attention analysis in online marketing. The research question we are trying to address is whether automated tools can be used to depict differences between brand related websites of beer companies. Automated and quick comparison of websites from different markets and cultures might provide stimulating and instructive feedback and thus become an invaluable tool for online marketers. In spite of being exploratory in nature, the study and indicates that the automated tools instead of human-centered attention analysis could be an inexpensive yet relevant tool for brand site development.
The advertising campaign is set according its goals and objectives. To ensure the highest efficiency of the campaign, the companies use different approaches to scheduling and timing the advertisements. There are different scheduling patterns identified to adjust the campaign timing according to the communication goals. The volume of advertising during the campaign may be continuous with steady (i.e. reminder advertising for matured products or building brand awareness), rising (i.e. to concentrate attention around a particular event) or falling (i.e. fade after initial launch of a new product) trend during the campaign. There are more scheduling pattern identified (i.e. flighting or pulsing) used for short and heavy advertising periods. The campaign length also reflects the nature of the communicated message and the goals of the campaign. For example longer campaigns (weeks or years) are often directed towards building the longer term effects of favorable brand image and strong brand loyalty.
Sentiment analysis and opinion mining is being perceived as one of the major trends of the nearest future. This issue follows up on the spontaneous and massive expansion of new media (esp. social networks). The amount of the usergenerated content published on social networks significantly increases every day and becomes an important source of information for potential customers. More than 75 % of the users confirm that customer’s reviews have a significant influence on their purchase and they are willing to pay more for a product with better customer reviews. Furthermore one third of the users has posted an online review or rating regarding a product or service and thus became an influencer himself. Using sentiment analysis, company can take advantage to get insight from (social) media, recognize company or product reputation or develop marketing strategy responding to the negative sentiment and positively impact consumer’s perception. Moreover, top influencers and opinion makers can be identified for further cooperation. Even though social media monitoring is commonly carried out automatically (by tracking selected channel or by crawling the web and searching for given keywords) the analysis and interpretation of retrieved data is still often performed manually. Such unsystematic approach is then prone to subjective error and is dependent on the experience and skills of the person performing the analysis. Thus there is a strong call for automated methods (based on computer-based processing and modeling) which would be able to classify expressed sentiment automatically. Good results can be obtained with supervised learning models (i.e. support vector machine models). However, for a good performance a good training set is needed. Such approaches also often work with lexical databases (i.e. WordNet) or sentiment vocabularies (identifying polarity keywords with the sentiment clearly distinguished i.e. “horrible”, “bad”, “worst”). These models do not work very well when the training set comes from different domain than the testing data and also not many studies have addressed sentiment analysis issue for morphologically rich languages, i.e. Arabic, Hebrew, Turkish or Czech. This experiment tries to develop and evaluate a sentiment analysis model for Czech language (which is morphologically rich) which is not dependent on any prior information (lexical databases or sentiment vocabularies which are not available for Czech language) and works well on different domains. As training set data from Czech-Slovak Film Database were used. The support vector machine based classification model has been then tested on different domain (data from an e-shop selling a wide range of products from electronics to clothing or drugstore goods). With a good results (accuracy around 80 %), the model has been also tested on other languages, including Amazon customer reviews in English (Amazon.com, Amazon.co.uk), German (Amazon.de), Italian (Amazon.it) and French (Amazon.fr). Even on other languages, the model still provided a good performance ranging from 70 to 80 %. This may not sound impressive but there are studies reporting that human raters typically agree about 80 % of the time. Thus if an automated systems were absolutely correct about sentiment classification, humans would still disagree with the results about 20 % of the time (since they disagree at this level about any answer).
Developers use a variety of methods to evaluate user’s reactions to the website. Research in neuroscience and natural vision processing resulted in the development of automated methods which simulate human attention and are able to provide similar results to eye-tracking. However robust evidence is still missing.
This study contributes and expands on this debate. Eye-tracking studies on cultural differences confirmed that users from different cultures have different expectations and preferences. This study answers the question whether cultural differences in web design could be revealed also by automated attention analysis. Websites of the largest beer producers from different countries with different cultural background were analyzed through automated attention analysis tool to determine whether there is a difference in the number of potential areas of interest and their size. The study confirms that automated tools can depict cultural differences and thus provide fast and inexpensive results for initial assessment of website interfaces.
At this time all people, especially managers and businessmen, are exposed to the ever-present information pollution. This is why tools of business intelligence are of great importance; nevertheless the current methods can hardly cope with large and unstructured text sources like World Wide Web that currently becomes more and more important. To achieve this main goal we have to find and verify satisfactorily reliable methods for automatic extraction of a main context of a document, i.e., multidimensional structured characterization representing the main topic of the document. To cope with the multilingual sources we have to develop approaches that would not be dependent on the language of the source and that would not need any additional language dependent tools (like thesauri). In our conception, the context is dynamic – it means that a classification of a document will not be dependent only on the document in question but also on the corpus; the expansion of a corpus can result in a change of a document classification.
The study compares and contrasts attributes of user perceived quality with information websites. It concerns a study of the formation of website quality, its nature and evolution based on the fulfillment of typical tasks. Based on empirical study based on 44 information websites, information value and navigation have been identified as key ingredients perceived by website users when judging website quality. Color scheme assessment was found to predict successful task fulfillment.
Automobilový průmysl zaměstnává v rozvinutém světě mnoho pracovníků a tvoří významnou část průmyslové produkce. Skokový pokles poptávky po nových vozech způsobený zhoršenou dostupností financování i spotřebitelskými obavami z budoucnosti přiměl v závěru roku 2008 a v roce 2009 mnohé vlády k zavedení šrotovného – v podstatě dotačního programu podporujícího obnovu vozového parku v zájmu snížení emisí či zvýšení bezpečnosti provozu. Vyvstává otázka, zda tyto programy pouze nepřesouvají poptávku v čase a neurychlují nákup nového vozu, který by byl za jiných podmínek realizován později. Tento příspěvek se snaží nalézt odpověď na tuto otázku.
Substantial body of marketing and consumer behavior literature is devoted to the phenomenon of consumer satisfaction, its antecedents, attributes and consequences. This study, based on a survey among 160,000 car owners in five major European markets compares and contrasts product satisfaction in light of satisfaction with shopping experience. In other words, the paper addresses an important marketing question whether shopping event fosters positive product experience.
Based on quantitative analysis, the findings suggest there is no relationship between satisfaction with purchase and satisfaction with a product. The distinction between purchase and product satisfactions implies that a customer clearly differentiates between a product itself (car company) and purchase experience (dealers) not perceiving the car as a total product.
Important implications for marketing and product managers of car producers may suggest far lesser involvement in showroom and dealer development in search for satisfied customers. Similarly, the study would imply that marketing managers of dealerships can do little for improving product-related experience and should, therefore, focus on the purchase itself and surrounding services such as financing. Theory-wise, the concept of total product may need to be reconsidered.