Background: In recent years, the emerging electronic cigarette (e-cigarette) marketplace has developed prosperously all over the world. By analyzing online e-liquid reviews, we seek to identify the features attracting users. Methods: We collected e-liquid reviews from one of the largest online e-liquid review websites and extracted the e-liquid features by keywords. Then we used sentiment analysis to classify the features into two polarities: positive and negative. The positive sentiment ratio of a feature reflects the e-cigarette users' preference on this feature. Results: The popularity and preference of e-liquid features are not correlated. Nuts and cream are the favorite flavor categories, while fruit and cream are the most popular categories. The top mixed flavors are preferable to single flavors. Fruit and cream categories are most frequently mixed with other flavors. E-cigarette users are satisfied with cloud production, but not satisfied with the ingredients and throat hit. Conclusions: We identified the flavors that e-cigarette users were satisfied with, and we found the users liked e-cigarette cloud production. Therefore, flavors and cloud production are potential factors attracting new users.

The diploma thesis is focused on smartphones and user product reviews. The purpose of the diploma thesis is to establish a link between user product reviews and their willingness to buy the product. The thesis is divided into two parts. The theoretical part deals with consumer behavior, brands, willingness to buy a product and user product reviews. In the practical part there is a research demonstrated. The research is applied on a target group of czech consumers in the age from 16 to 24. In the last part of the thesis there is an evaluation and some recommendations. These recommendations can help to realize the key aspects which influence the customers willingness to buy the product.

Empowered by information technology, modern consumers increasingly rely upon online word-of-mouth (WOM--e.g., product reviews) to guide their purchase decisions. This dissertation investigates how WOM information is processed by consumers and its downstream consequences. First, the value of specific types of word-of-mouth information (e.g., numeric ratings, text commentary, or both) was explored for making forecast. After proposing an anchoring-and-adjustment framework for the utilization of WOM to inform consumer forecasts, I support this framework with a series of experiments. Results demonstrate that the relative forecasting advantage of different information types is a function of the extent to which consumer and reviewer have similar product-level preferences ('source-receiver similarity'). Second, I investigate the process by which dispersion--the degree to which opinions are divided for a product or service--in WOM is interpreted. Using an attribution-based approach, I argue that the effect of WOM dispersion is dependent on the perceived cause of that dispersion, which is systematically related to perceptions of preference heterogeneity in a product category. For products for which preferences are expected to vary, dispersion is likely to be attributed to the reviewers rather than the product itself, and therefore tolerated. I provide evidence for my hypotheses in a series of experiments where WOM dispersion is manipulated and respondents make choices and indicate purchase intentions.

Submitted by Lúcia Brandão (lucia.elaine@live.com) on 2015-12-11T18:38:02Z No. of bitstreams: 1 Dissertação - Onilton de Oliveira Maciel Junior.pdf: 1323945 bytes, checksum: 1dbe56bb277d786c9dda5294abe9e8dc (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2016-01-20T18:33:35Z (GMT) No. of bitstreams: 1 Dissertação - Onilton de Oliveira Maciel Junior.pdf: 1323945 bytes, checksum: 1dbe56bb277d786c9dda5294abe9e8dc (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2016-01-20T18:39:45Z (GMT) No. of bitstreams: 1 Dissertação - Onilton de Oliveira Maciel Junior.pdf: 1323945 bytes, checksum: 1dbe56bb277d786c9dda5294abe9e8dc (MD5) / Made available in DSpace on 2016-01-20T18:39:45Z (GMT). No. of bitstreams: 1 Dissertação - Onilton de Oliveira Maciel Junior.pdf: 1323945 bytes, checksum: 1dbe56bb277d786c9dda5294abe9e8dc (MD5) Previous issue date: 2013-03-28 / FAPEAM - Fundação de Amparo à Pesquisa do Estado do Amazonas / Eletronic commerce, which has retailers of the most variable sizes, is one of the most profitable segments of the web. Every day, a large number of users buys products through those websites, in a process that, not rarely, begins with a search for product information. The product reviews available at online stores are tools thathelpthisprocessbyprovidingotherusersimpressionsaboutaproduct,without demanding any effort from the user for him to get more information. This tool, however, have some limitations, among them, the amount of reviews available and the difficulty to obtain them. Therefore, in this work, we present a method that, using a external database of documents, can be utilized to find and show reviews in the pages of the corresponding product. Our experiments show that our proposal is a practicable alternative to improve the user experience in eletronic commerce websites. / O comercio eletrônico exercido por varejistas dos mais diversos tamanhos através de suas lojas virtuais é um dos mais lucrativos segmentos da web. Diariamente, um grande número de usuários realiza a compra de produtos através desses sites, em um processo que, não raramente, inicia-se por uma pesquisa sobre diversas informações do produto. As revisões de produto existentes nas lojas virtuais são uma ferramenta que visa auxiliar esse processo ao prover opiniões de outros usuários a respeito de um produto, sem demandar esforço do usuário para obter tais informações. Essa ferramenta, no entanto, possui algumas limitações, entre elas, a quantidade de revisões disponíveis e a dificuldade em obte-las. Por esse motivo, neste trabalho, apresentamos um método que, utilizando uma base externa de documentos candidatos, pode ser utilizado para encontrar e exibir revisões nas páginas dos produtos correspondentes. Nossos experimentos demonstram que nossa proposta é um alternativa viável para melhorar a experiência dos usuários em sites de comércio eletrônico

The main goal of this diploma thesis is to prove whether there is a relationship between the willingness to buy and the user product reviews. Sectional questions are related to e.g. the willingness to pay more for the product with a better review, to a satisfactory number of stars in a rating or to what is crucial for customers when choosing a product. The readers are introduced to basic concepts related to the topic (such as the purchase behavior of customers and its influences, the willingness to buy, the customer satisfaction or the user product reviews) before the analysis. The interviewing method was chosen for primary data collection. Due to a quantitative nature of the research, the research questions were specified firstly. These questions were evaluated using descriptive statistics and tools of statistic reasoning.

Online word-of-mouth (WOM) platforms have been referred to by various terms such as online communities, feedback systems, peer reputation systems, or consumer generated media. Such systems provide a global platform for customers to share their experiences, and also rate service providers. WOM systems are burgeoning on the Internet for products such as music and books (Amazon.com), news (Slashdot.org), consumer electronics (shopping.com), tourism and travel (Tripadvisor.com; Hotels.com), and many other products and services. As with the traditional WOM, numerous studies have shown that these systems have a significant impact on customer decision making process, their satisfaction with goods and services, and the overall value of online economic transactions. In this study, the primary focus were the product review systems (PRS). These review systems are less personal but more ubiquitous platforms for online WOM wherein consumers post reviews about the products/services they have consumed. These reviews are widely accessible to other consumers but are disseminated only when other consumer consult these reviews during the purchasing process. However, there are still numerous problems associated with these systems. Recent studies have shown that there are numerous instances of deceptive information provided by service providers themselves or customers who have been paid by commercial parties. Added to this is the problem of anonymity in a computer mediated environment that adds to the already existing uncertainty for the consumer. Further, each review system consists of hundreds of consumer reviews associated with any given product or service. Given that consumers face these numerous problems, research is yet to examine the factors that drive the consumers develop trust in these reviews, and base their purchasing decisions on the information gleaned from the review systems. The main objective of this study was to explore this interesting phenomenon. To this end, this study applied uncertainty reduction theory and Social identity theory to delineate certain aspects of the online reviews that might have an impact on the consumer's assessment of online product reviews. Based on these theories, it was hypothesized that the informational content of the review and social component of the review (individuals' identity information disclosure and the consumers' perceived similarity with this information) have a significant effect on the consumers' trust in a review and subsequently the purchase intention. Further, based on the elaboration likelihood model, it was also posited that consumers' use of these heuristics is more salient while evaluating high involvement products than low involvement products. To test the hypotheses, the study adopted a quasi-experimental design with 2x2 (2 levels each for information content and social component within-subjects) x 2 (2 involvement modes between-subjects) full factorial design. Based on two levels for each of these factors, four reviews similar to those found in sites such as tripadvisor.com were created. A total of 283 students (153 in high involvement mode and 130 in low involvement mode) evaluated these reviews and assigned trust scores as well purchase intention scores to each review. The data was analyzed using linear mixed models and structural equation modeling. The results showed that both the main effects, information content of the review, and the consumers' perceived social identity with the reviewer contribute to an increased trust in the reviews. The study data did not support the hypothesis that involvement of the activity moderates the above mentioned relationships. Within this, information content was found to be playing an important role in both the involvement modes whereas the social component explained more variance in the trust in the high involvement mode than low involvement mode. Some of the results concur with previous research in both traditional and online WOM. The significance of these results in the extant literature as well their implications for both product review system providers as well tourism and hospitality service providers are discussed in detail. / Business Administration

Sentiment analysis of Swedish data is often performed using English tools and machine. This thesis compares using a neural network trained on Swedish data with a corresponding one trained on English data. Two datasets were used: approximately 200,000 non-neutral Swedish reviews from the company Prisjakt Sverige AB, one of the largest annotated datasets used for Swedish sentiment analysis, and 1,000,000 non-neutral English reviews from Amazon.com. Both networks were evaluated on 11,638 randomly selected reviews, in Swedish and in English machine translation. The test set had the same overrepresentation of positive reviews as the Swedish dataset (84% were positive). The results suggest that English tools can be used with machine translation for sentiment analysis of Swedish reviews, without loss of classification ability. However, the English tool required 33% more training data to achieve maximum performance. Evaluation on the unbalanced test set required extra consideration regarding statistical measures. F1-measure turned out to be reliable only when calculated for the underrepresented class. It then showed a strong correlation with the Matthews correlation coefficient, which has been found to be more reliable. This warrants further investigation into whether the correlation is valid for all different balances, which would simplify comparison between studies. / Attitydanalys av svensk data sker i många fall genom maskinöversättning till engelska för att använda tillgängliga analysverktyg. I den här uppsatsen undersöktes skillnaden mellan användning av ett neuronnät tränat på svensk data och av motsvarande neuronnät tränat på engelsk data. Två datamängder användes: cirka 200 000 icke-neutrala svenska produktomdömen från Prisjakt Sverige AB, en av de största annoterade datamängder som använts för svensk attitydanalys, och 1 000 000 icke-neutrala engelskaproduktomdömen från Amazon.com. Båda versionerna av neuronnätet utvärderades på 11 638 slumpmässigt utvalda svenska produktomdömen, i original och maskinöversatta till engelska. Testmängden hade samma överrepresentation av positiva omdömen som den svenska datamängden (84% positiva omdömen). Resultaten tyder på att engelska verktyg med hjälp av maskinöversättning kan användas för attitydanalys av svenska produktomdömen med bibehållen klassificeringsförmåga, dock krävdes cirka 33% större träningsdata för att det engelska verktyget skulle uppnå maximal klassificeringsförmåga. Utvärdering på den obalanserade datamängden visade sig ställa särskilda krav på de statistiska mått som användes. F1-värde fungerade tillfredsställande endast när det beräknades för den underrepresenterade klassen. Det korrelerade då starkt med Matthews korrelationskoefficient, som tidigare funnits vara ett pålitligare mått. Om korrelationen gäller vid alla olika balanser skulle jämförelser mellan olika studiers resultat underlättas, något som bör undersökas.

Submitted by Maike Costa (maiksebas@gmail.com) on 2016-05-16T13:15:08Z No. of bitstreams: 1 arquivo total.pdf: 6619153 bytes, checksum: ab30577da64fe07f90d28f172fea6661 (MD5) / Made available in DSpace on 2016-05-16T13:15:08Z (GMT). No. of bitstreams: 1 arquivo total.pdf: 6619153 bytes, checksum: ab30577da64fe07f90d28f172fea6661 (MD5) Previous issue date: 2015-04-06 / Statistical process control is becoming increasingly important in the pharmaceutical industry, since it can act on the product quality assurance and monitoring of production efficiency. Regulatory agencies worldwide already include multivariate statistical process control on their recommendations. In this work we perform three applications of multivariate control charts to detect small variations in monitoring pharmaceutical process. The studies were performed in the Laboratório Farmacêutico do Estado de Pernambuco Governador Miguel Arraes - LAFEPE using process data and addressing real problems of the industry routine. The first one consists in the elaboration of the Annual Product Review using multivariate control charts based on Principal Component Analysis, accompanied by a simple and unique methodology for identification of multivariate signal out of control, which was performed by decomposition of T2 statistics based on the loadings of VARIMAX rotation. The method developed has allowed the sector responsible for the Quality Assurance industry to verify the variables that most impact the process. The second application consists in monitoring of the degradation of captopril in tablets by High Performance Liquid Chromatograph measurements. For this aim multivariate control charts based on residuals of principal component analysis were built. The weighting of the retention time of the chromatogram in the region of captopril disulfide highlights the residual chart for revealing slight changes in the chromatographic standards. The third and last application consists in monitoring of the degradation of captopril in tablets by near infrared and middle infrared measurements. For this aim T2 control charts were built by using a variable selection method and a CUSUM-COT scheme. Both the techniques showed to be able for detection of expired samples and Middle infrared was able to identify slight changes during degradation process. Keywords: Monitoring of Process, Multivariate Control Charts, Annual Prod / O controle estatístico de processos vem ganhando importância na indústria farmacêutica, uma vez que pode atuar na garantia da qualidade do produto e no monitoramento da eficiência da produção. Agências regulatórias no mundo já incluem o controle estatístico de processos multivariado em suas recomendações. Neste trabalho realizamos três aplicações de cartas de controle multivariadas para detectar pequenas variações em processos na indústria farmacêutica. Os estudos foram realizados no Laboratório Farmacêutico do Estado de Pernambuco Governador Miguel Arraes - LAFEPE, empregando dados do processo e abordando problemas reais da rotina da indústria. A primeira aplicação consiste na elaboração da Revisão Periódica de Produtos empregando cartas de controle multivariadas baseadas em Análise de Componentes Principais, acompanhada de uma metodologia simples e original para identificação do sinal multivariado fora de controle por meio da decomposição da estatística T2 com base nos pesos da rotação VARIMAX. O procedimento desenvolvido permitiu monitorar e diagnosticar os desvios no processo produtivo, além de permitir ao setor responsável pela Garantia da Qualidade verificar as variáveis que mais impactaram o processo. A segunda aplicação é demonstrada em estudos de estabilidade de medicamentos empregando Cromatografia Líquida de Alta Eficiência. No estudo de estabilidade a carta de resíduos das componentes principais permitiu monitorar o processo de degradação de comprimidos de captopril. A ponderação do cromatograma na região do dissulfeto de captopril sensibiliza a carta de resíduos para revelar alterações sutis no padrão cromatográfico. A terceira aplicação envolve estudos de estabilidade empregando a espectroscopia no infravermelho próximo e médio. Nesta aplicação, conclui-se que ambas as técnicas são eficientes em detectar amostras vencidas. O Processo de degradação do captopril pode ser acompanhado pela carta de resíduos baseada nos espectros do infravermelho próximo. No infravermelho médio, a carta T2 construída com um método de seleção de variáveis e um esquema CUSUM-COT também foi eficiente em detectar as pequenas alterações durante o processo de degradação.