Highlights

Abstract

Keywords

1. Introduction

2. Related work

3. Proposed method

4. Case study: user controversial behaviour in online data service

5. Experiment and discussion

6. Conclusion and future work

CRediT authorship contribution statement

Acknowledgments

References

Vitae

Abstract

Nowadays, online word-of-mouth has an increasing impact on people’s views and decisions, which has attracted many people’s attention.The classification and sentiment analyse in online consumer reviews have attracted significant research concerns. In this thesis, we propose and implement a new method to study the extraction and classification of online dating services(ODS)’s comments. Different from traditional emotional analysis which mainly focuses on product attribution, we attempted to infer and extract the emotion concept of each emotional reviews by introducing social cognitive theory. In this study, we selected 4,300 comments with extremely negative/positive emotions published on dating websites as a sample, and used three machine learning algorithms to analyze emotions. When testing and comparing the efficiency of user’s behavior research, we use various sentiment analysis, machine learning techniques and dictionary-based sentiment analysis. We found that the combination of machine learning and lexicon-based method can achieve higher accuracy than any type of sentiment analysis. This research will provide a new perspective for the task of user behavior.

1. Introduction

As global Internet presentations continue to increase, the number of consumers who provide online comments have increased significantly (Lu & Bai, 2021). If exploited properly, abundant data should produce useful insights. One insight that can be obtained from the statistics is the information of electronic word of mouth (EWOM). EWOM is known for its significant impact on consumer behavior (Tobon & García-Madariaga, 2021). EWOM communication framework demostrates the direct relation of adopting EWOM and consumers’ willingness to purchase. EWOM can provide objective information for more and more consumers who trust these communications (Yaniv & Shalom, 2021).Comment mining concerning sentiment analysis is considered to be a suite of proceedings for identifying sentiments, opinions and author’s attitudes in texts, transforming them into meaningful information and using them to make business decisions (Siddiqui et al., 2021).

Sentiment classification identifies opinions and arguments in a given text, and it is part of opinion mining. It tries to find statements of agreement or disagreement in comments or reviews that involve positive, negative or neutral statements. Sentiment analysis has attracted widespread attention and has been widely used in many fields (Wang & Zhang, 2020). Up to now, many approaches of sentiment analysis have been proposed, which can be roughly split into document-level, sentence-level and aspect-level(Jiang, Chan, Eichelberger, Ma, & Pikkemaat, 2021).Most of the work of sentiment analysis can be achieved by assessing the document’s polarity.Phrase and sentence levels have become common increasingly in recent years.Dictionary-based and machine learning approaches are two of the most common uses of emotion analysis(Ahlem & Khalil, 2020).

Abstract

1. Introduction

2. Literature Review

3. Research Hypotheses and Proposed Model

4. Methods

5. Results

6. Discussions

7. Conclusions

Appendix A

References

Abstract

     This study is focused on communications that come from consumer-to-consumer (C2C) ecommerce relationships. This topic is directly associated with the electronic word-of-mouth (eWOM) phenomenon. eWOM is related to the set of positive or negative opinions made by potential, actual, or former customers about a seller. The present study proposes a structural equation modeling with partial least squares (PLS-SEM) research model to analyze consumers’ opinions impact on attitude toward purchasing. This model is based on the Information Adoption Model (IAM) in combination with an ecommerce satisfaction perspective, comprising five constructs: (1) service quality, (2) ecommerce satisfaction, (3) argument quality, (4) source credibility and (5) purchase intention. The model was tested by applying the Smart Partial Least Squares (SmartPLS) software for which 116 effective data from customers of the Taobao C2C platform were used. The findings reveal that all of the defined relationships were supported, confirming the positive impact of all the proposed constructs on the purchase intention. In this respect, the findings suggest that C2C platforms should strengthen the analyzed connections to grow the business and to promote transactions. Finally, implications and limitations related to the explanatory capacity and the sample are identified.

Introduction

     In recent years, many consumer-to-consumer (hereafter, C2C) ecommerce platforms have emerged [1]. Considering the type of goods, some remarkable examples can be identified, such as Avancar, SocialCar or Blablacar for car-sharing or rental services; Airbnb for accommodations; or Wallapop and Taobao for second-hand goods [2,3], among many others. This phenomenon is also known as collaborative consumption. In fact, some authors have considered it as a reinvention of traditional markets [4], such as bartering or exchange. In this manner, collaborative consumption can now be developed on a global scale thanks to technology [5], promoting the reasonable use of goods [6].

     In this context, the success of these platforms is largely determined by the registered opinion of its users [7]. In this sense, consumers frequently make decisions related to purchases only under the influence of opinions exposed by other consumers [8]. In fact, the shopping experience is as important as sharing this shopping experience to influence the purchase process [9]. Thus, this study is associated with the topic of electronic wordof-mouth (eWOM) relationships. In this respect, according to [10], eWOM refers to “any positive or negative statement made by potential, actual, or former customers about a productor company, which is made available to a multitude of people and institutions via the Internet”

Results and analyses

     The present work was an attempt to test the purchase intention in C2C platforms, mainly applying the IAM framework. In this respect, the definition of a PLS-SEM model allowed to draw relevant conclusions about the role of information transmission coming from online communications in C2C relationships. In addition, based on the findings obtained, it was possible to identify the factors that, within the C2C, incentivize purchase intention. They include (1) service quality, (2) ecommerce satisfaction, (3) argument quality and (4) source credibility. In fact, the findings have provided useful data for clarifying the most relevant factors that impact purchase intentions. Overall, the present analysis clearly confirms that the success of C2C platforms could be determined by dimensions related to the direct relationships between consumers, which allow generating trust to complete a purchase. In a similar way, in answering the research question, we can affirm the validity of IAM to explain the eWOM impact on purchase intention in combination with an ecommerce satisfaction perspective.

     plications are proposed. First, this study extended knowledge about C2C ecommerce. In this way, additional empirical evidence has been provided for ulterior research to evaluate the purchase intention in C2C enabling new advances in the field. Second, adopting a managerial view, comprehending the dimensions associated with online purchases is profitable for the C2C online platforms. In this manner, these findings suggest that C2C platforms should strengthen the analyzed connections to grow the business and to promote transactions.

1- Introduction

2- Literature review

3- Conceptual framework and hypotheses development

4- Methodology

5- Results

6- Discussions

7- Conclusions

References

Abstract

In recent times, waste management has engaged the attention of governments, policy makers, and academics as it has ramifications for the health and well-being of citizens, the environment, and the economy. In this regard, waste management firms and policy makers are employing strategic approaches to waste management efforts by empowering relations among various stakeholders to innovate. Thus, customer and stakeholder value co-creation is one such strategic approach waste management firms can adopt to create value and to brand. Previous studies of co-creation in waste management are largely broad in perspective. The purpose of this study is, therefore, to assess the relationship among customer operant resources, online value co-creation and digital branding through electronic word-of-mouth in the Ghanaian waste collection industry. Using the positivist research paradigm approach, a structured questionnaire was used to collect data from customers through social media platforms. Hierarchical multiple regression was used to test the hypotheses. The relationships among customer operant resources, co-creation and electronic word-of-mouth were all significant. Customer value co-creation positively mediates between customer operant resources and electronic word-of-mouth. Firm web-based platforms also positively moderate the effects of customer operant resources on customer online value co-creation. The results of the study can guide management of the firms to design appropriate strategic and educational programs for the customers. This study has advanced knowledge on the importance of customer operant resources in waste management value co-creation by demonstrating the degree of impact of each of these customer resources.

Introduction

In recent times, internet-based platforms have become sources of rich knowledge and skills from consumers, and for that reason firms are tapping into these resources to create value for the market. Thus, customer online value co-creation is one strategy organizations are using to create value and to brand, particularly, in the area of product advocacy. Waste management has engaged the attention of governments, policy makers, and academics much more recently as it has ramifications for the health and well-being of citizens and the environment, and subsequently on the economy. In this regard, waste management firms and policy makers should view waste management efforts as a strategic decision and not as a tactical decision (Esmaeilian et al., 2018).Therefore, the strategic planning for waste management must focus on increasing productivity through empowering relations among various stakeholders (Esmaeilian et al., 2018; Fuldauer et al., 2019). According to literature, this approach improves waste management efficiency and lower cost of operation (Lu and Sidortsov, 2019). Africa is experiencing rapid urbanization, with high urban population growth rates.

Introduction

Conceptual framework

Methods

Results

Discussion

Practical implications

Conclusions

Limitations and recommendations for future studies

References

Abstract

Purpose – The purpose of this paper is to contribute to the marketing literature regarding Islamic countries, in particular the United Arab Emirates (UAE), by assessing the impact of electronic word of mouth (e-WOM) on brand image and on the online purchase intentions of consumers.
Design/methodology/approach – Using a descriptive research approach, this study used quantitative data to assess how the online purchase intentions of consumers in the UAE are influenced by e-WOM and brand image. Findings – E-WOM has a significant impact on online purchase intentions and brand image among consumers. Brand image significantly influences the online purchase intentions of consumers.
Research limitations/implications – The conclusions may not be generalizable because not all areas of the UAE were represented in this study. In future studies, a larger and more inclusive sample would help to overcome this limitation.
Practical implications – This study will help marketers to understand the power of e-WOM, an important marketing tool, and to use resources more strategically to attract new customers. Originality/value – E-WOM is the most commonly used and most effective medium of sharing opinions and reviews pertaining to various products and services in the market. Understanding how it influences the purchase intentions of consumers is imperative and has strong implications for marketers.

Introduction

Traditional word of mouth (WOM) was one of the earliest modes of communication (Mayzlin and Chevalier, 2003; Chevalier and Mayzlin, 2006). Over the years, researchers have explained this term in a variety of ways (Dellarocas, 2003; Xia and Bechwati, 2008; HueteAlcocer, 2017). Katz and Lazarsfeld provided the earliest explanation in the late 1960s, describing it as an important means of exchanging product-related information among consumers (Katz and Lazarsfeld, 1966). They and Trusov et al. (2009) were of the view that WOM is a very influential tool for marketing, as it holds the potential to form and influence the behavior of consumers toward a product or service. With advances in information technology, the use of the internet and social media have become extremely widespread; they have greatly influenced the modes of communication used and preferred by people (Chan and Ngai, 2011).

It becomes more and more important for marketers to understand why individuals adopt electronic word-ofmouth (e-WOM) on social networking sites. This paper aims to understand the social networking sites users eWOM adoption based on the attachment theory. Attachment avoidance, attachment anxiety, and their interaction effects are tested to understand the direct effect on e-WOM adoption. Moreover, the mediating effect of self-surveillance and social surveillance between attachment styles and e-WOM adoption has also evaluated. The results indicated that attachment avoidance has an adverse effect on e-WOM adoption; attachment anxiety and the interactive effect have a positive effect on e-WOM adoption. Self-surveillance and social surveillance have a mediating effect between two attachment dimensions (avoidance and anxiety) and e-WOM adoption, and the interaction of anxiety and avoidance mediated by social surveillance.

Introduction

Electronic word-of-mouth (e-WOM) is becoming an important marketing tool in the social media era. Consumers are accustomed to sharing information with others on social networking sites (SNSs), such as Facebook or Twitter. e-WOM is defined as “any positive or negative statement made by potential, actual, or former customers about a product or company, which is made available to a multitude of people and institutions via the Internet” (Hennig-Thurau, Gwinner, Walsh, & Gremler, 2004, 39). Prior e-WOM related studies are classified into two levels: marketlevel analysis and individual-level analysis (Lee & Lee, 2009). The objective panel data (e.g., amount of consumer reviews) were used in the market-level analysis to measure the impact of e-WOM on product sales (Chen & Xie, 2005; Chevalier & Mayzlin, 2006). Subjective personal factors (e.g., source credibility and consumer knowledge) were used in the individual-level analysis (Cheung, Luo, Sia, & Chen, 2009; Park & Kim, 2009). Individual-level analysis based e-WOM studies focus on four main elements in social communication: communicator (source), stimulus (content), receiver (audience), and response (main effect) (Cheung & Thadani, 2012). Communicators share or generate the contents for receivers, and receivers respond to the communicators.

To date there is limited research on the role of customer perceived value for reading and giving positive and negative electronic word-of-mouth (eWOM) of an altruistic service within a singular study. Further, emotions have been shown to be important in altruistic services, yet there is no investigation of the role of emotional value for eWOM. This paper investigates these gaps by proposing and empirically testing a model with data from an online survey of 366 consumers of an altruistic service (blood donation) using structural equation modelling. The results show emotional value is a central value concept that mediates the relationship between reading eWOM and other value dimensions, whereas altruistic value is shown to be important for giving eWOM. The findings have theoretical importance for understanding the nature of customer perceived value in altruistic services and are also useful to managers of altruistic services seeking to increase eWOM as a customer recruitment and retention strategy.

Introduction

Altruistic services, whereby consumers take active roles in civic participation through volunteering and donating time and effort to assist in creating a service, are becoming increasingly important to address many global issues such as blood shortages and natural disasters (Cheung, McColl-Kennedy, & Coote, 2017). However, many altruistic service organisations have limited resources (e.g. infrastructure, staff and funding), which can hinder their ability to provide service offerings and also to recruit and retain consumers who assist in their creation (Alfes, Antunes, & Shantz, 2017). Dropping rates of consumer participation in altruistic services is of increasing concern in countries such as the United States (Ellingson et al., 2017), the United Kingdom (Office for National Statistics [ONS], 2017) and Australia (Oppenheimer, Haski-Leventhal, Holmes, Lockstone-Binney, & Meijis, 2015). Scholars and practitioners have called for greater theoretical and practical insights into how such trends can be reversed, and consumers retained or recruited to ensure altruistic services are sustainable and continue to deliver important, and at times vital, services to the community.

1- Introduction

2- Related works

3- Problem formulation and methodology

4- Empirical study

5- Conclusions

References

Abstract

The identification of top persuaders from social networking websites is increasingly attracting attention because they can significantly affect consumers’ purchasing decisions in electronic word-of-mouth (eWOM) marketing. Existing studies on the identification of top persuaders have mainly focused on the idea of trust and have not considered distrust. However, this omission may lead to a high negative impact of the top persuaders identified from trust networks. To address this issue in the context of mixed trust networks, this study formulates the top persuader identification problem and develops a novel approach to identifying top persuaders. The structural properties of mixed trust networks are investigated through four measures: the degree of distribution, the correlation coefficient of trust and distrust, the cumulative distribution of the ratio between the degree of distrust and the degree of trust, and the mix pattern. To adapt to the context of mixed trust networks, a mixed trust PageRank (MTPR) index is conceived to evaluate the influential power of a top persuader. Reinforced by the dimensions of trust and distrust, the MTPR-based approach is proposed to identify top persuaders in mixed trust networks. The experimental results using real-world data collected from Epinions show that the proposed approach outperforms the degree centrality approach and the PageRank approach.

Introduction

In the digital era, Internet-based social communication services (e.g., Twitter, MySpace, Facebook, and LinkedIn) have resulted in the emergence of social persuasion as a complex force that governs the propagation of influence in online social networks (OSNs) [1–3]. Social persuasion is closely related to social contagion and network diffusion, by which a consumer’s attitude, belief, or behavior is influenced by other consumers in an OSN [4]. This phenomenon has allowed various companies to identify top persuaders who can propagate social influence through their high network status in OSNs and who have the ability to affect the behavior and attitudes of other consumers [5–7]. Therefore, the ability to discover top persuaders in an OSN has become critical to companies in electronic word-of-mouth (eWOM) marketing [8– 10]. In this context, marketing information can be diffused faster and be promoted better by top persuaders to their followers in OSNs via word of mouth.

Marketers have fully embraced social media, with over 96% of businesses using social media as a marketing tool and 92% saying social media is important to their business goals (Stelzner, 2015). Heralded as a new paradigm in marketing, social media stands to give consumers a powerful and undeniable voice in their relationships with organizations. Marketing communication is now evolving toward two-way conversations ratherthan one-way, mass-media sermons. However, influential and frequently negative consumer comments on social media have left many companies unsure of how to address public criticism; marketers cite negative consumer response on their social media sites as their number one fear (Gillin, 2009). Many companies have experienced the sting of widespread negative social media backlash from consumers, resulting in bad press, falling stock prices, forced reversals on social issues and, in some extreme cases, in businesses closing their doors altogether (Grégoire, Salle, & Tripp, 2015; Kim, Wang, Maslowska, & Malthouse, 2016). Consumers have quickly embraced social media as an outletfor complaints. A growing percentage of consumers would rather contact a company to complain via social media as opposed to in-person or on the telephone (Gesenhues, 2013), yet 64% of consumers report that their customer service inquiries were not resolved via social media. When consumer issues are not addressed on social media in a timely manner, 38% ofrespondents will have more negative attitudes toward a brand and 60% are more likely to take a negative action toward the brand in terms of negative word-of-mouth, escalating complaints through other avenues, and buying less from the company or switching altogether (Gesenhues, 2013). Seventy-two percent of consumers expect brands to respond to complaints on Twitter within an hour. The benefits of meeting consumer expectations when responding to social media complaints are obvious; timely and satisfactory responses to complaints resulted in 47% of consumers more likely to recommend the brand through social media and increased purchase intentions for 34% of consumers (Gesenhues, 2013). Other studies indicate that consumers will spend 21% more if they receive good customer service through social media sites (Bennett, 2012).

Promotion is a common form of product sales. The third-party advertising on mass media such as TV and newspaper has long been taken as the major means of promotion. However, this promotion strategy suffers from expensive cost [1, 2]. Furthermore, it has been found that, beyond the early stage of product promotion, the efficacy of advertising diminishes [3]. Word-of-mouth (WOM) communications are a pervasive and intriguing phenomenon. It has been found that satisfied and dissatisfied consumers tend to spread positive and negative comments, respectively, regarding the items they have purchased and used [4, 5]. As compared to positive comments, negative comments are more emotional and, hence, are more likely to influence the receiver’s opinion. By contrast, positive comments are more cognitive and more considered [6–9]. The significant role of WOM in product sales is supported by broad agreement among practitioners and academics. Indeed, both positive and negative WOM will affect the purchase decision of potential consumers. Due to striking advantages such as significantly lower cost and much faster propagation, the WOM marketing outperforms the traditional advertising marketing [10, 11]. With the increasing popularity of online social networks such as Facebook, Myspace, and Twitter, the WOM marketing has come to be one of the main forms of product marketing [12]. Currently, the major concern on WOM marketing focuses on finding a set of seeds such that the expected number of individuals activated from this seed set is maximized [13]. Toward this direction, large number of seeding algorithms have been reported [14–23]. Additionally, a number of dynamic models capturing the WOM spreading processes have been suggested [24–34]. However, all the previous work builds on the premise that a single product or a few competing products are on sale. Typically, customers involved in a marketing campaign may purchase multiple products. The ultimate goal of such marketing campaigns is to maximize the overall profit. To achieve the goal, it is crucial to determine those factors that have significant influence on the overall profit. To our knowledge, so far there is no literature in this aspect. This paper addresses the modeling and analysis of the WOM marketing for a consistent set of items. First, a dynamic model, which is known as the SIPNS model, that characterizes the WOM marketing processes with both positive and negative comments is established. Second, a measure of the overall profit of a WOM marketing campaign is introduced. Third, the SIPNS model is shown to admit a unique equilibrium, and the equilibrium is figured out. Next, the impact of different factors on the equilibrium of the SIPNS model is expounded through theoretical analysis, and extensive experiments show that the equilibrium is much likely to be globally attracting. Finally, the impact of different factors on the expected overall profit of a WOM marketing campaign is ascertained through both theoretical analysis and simulation experiment. On this basis, some promotion strategies are recommended. To our knowledge, this is the first time the WOM marketing is modeled and analyzed in this way. The subsequent materials are organized as follows. Section 2 describes the SIPNS model, and presents a measure of the overall profit. Section 3 studies the SIPNS model. Section 4 reveals the influence of different factors on the expected overall profit. Finally, Section 5 closes this work.