Search results

The purpose of this paper is to examine how the sentiment of social networking site (SNS)-based brand-related electronic word-of-mouths (eWOMs) influences consumers’ engagement in brand value co-creation and brand trust change, thereby influencing their purchase intention for the brand; and explores a potential moderating effect of mavenism.

A sample of 237 college students participated in an online survey to report brand-related eWOM stories to which they were exposed and the brand trust change, brand value co-creation behavior and attitude and purchase intention in response to this exposure. The eWOM stories were content analyzed into positive vs negative eWOM. Structural equation modeling was used to test all hypotheses.

Participants reported a significantly higher level of brand value co-creation engagement behavior and more positive brand value co-creation engagement attitude and brand trust change after seeing a positive (vs negative) brand-related eWOM on SNSs. Brand trust change and value co-creation engagement attitude positively influenced purchase intention. The moderating effect of mavenism was not significant.

Findings suggest that brand marketers should actively monitor and respond to the sentiment of SNS-based eWOMs and establish strategies to encourage consumers to create and share positive eWOMs on SNSs.

This study contributes to closing the empirical gap in SNS-based eWOM research by providing support for brand-related eWOM sentiment as a significant motivational factor triggering consumers’ engagement in brand value co-creation and brand trust change on SNSs as well as purchase intention.

This paper aims to explore the image of travel destinations after the visit by analysing sentiment orientation of the online reviews, and how this orientation, as well as other electronic word of mouth (eWOM)’s credibility sources, can affect the perceived helpfulness of shared opinions measured through the helpfulness score.

Tourist destinations are increasingly affected by travel-related information shared through the Web. More and more people first check the previous travel experiences of other people to build their own destination image and to help them in their choice of destination. This paper analyses the shared opinions related to the city of Barcelona in a well-known eWOM website. The reviewers’ opinion and the credibility sources of eWOM are extracted from the web using a webscraper, while the sentiment score to analyse the discourse orientation (positive vs negative) is calculated using computer-based sentiment analysis techniques.

Online reviews’ users are reluctant to provide extreme polar opinions (very negative, very positive) to any travel subcategory (hotel, restaurant, attractions and night-life) of a tourist destination. The results obtained also reveal that eWOM’s perceived helpfulness grows with the expertise of the reviewer. However, the helpfulness score given to the reviews posted is not influenced by the sentiment orientation of the author’s opinion.

This research is limited to the case study of Ciao, which is a well-known consumer platform, and the city of Barcelona, which is a top touristic destination. However, the approach proposed can be easily extended to other similar consumer platforms and cities using the same methodology.

Understanding the information posted in the media environment is a major concern in the field of marketing destination planning. Positive and negative eWOM offers potential consumers a clear picture on the tourist destination, and this information can be used by Destination Marketing Organisations to meet customers’ needs and expectations. The perceived helpfulness of reviews analysed in this paper can also help practitioners and scholars to understand those factors that make reviews more trustable.

From a methodological point of view, the main contribution of this research is the utilisation of an unstructured approach to the measurement of the destination image based on the sentiment analysis of shared opinions. From a theoretical point of view, the study relates the post-visit destination image with the pre-visit image formation process, using the sentiment orientation of the former and the perceived helpfulness of the latter.

Industry and academic marketing researchers have attempted to predict consumer behavior from the volume and sentiment of social media activity. Yet, real-world examples demonstrate that individual and cultural factors may need to be built into current measures. This study aims to examine factors that differentiated sharers from non-sharers in regards to consumer sharing habits about entertainment products.

A survey of students at four large Southeastern Universities (n = 3,079).

Quantifying cultural work done about social media phenomenon, such as “Black Twitter”, many statistically significant differences were found between consumers. For example, women and African Americans shared their opinions far more frequently than other demos. Second, sharing habits greatly varied when considering the social media platform being used. Finally, respondents shared positive opinions about a product more than negative ones and sharing rates increased after a product’s release.

Although much consumer marketing research continues to analyze social media behavior based on volume and valence, this study found that other factors – such as consumer demographics, the social media platform being used and a consumer’s engagement with, and reaction to, a product – need to be added to marketing metrics.

This research aims to investigate the influence of electronic word-of-mouth (eWOM) on the diffusion rate of innovation in the context of entrepreneurial firms in emerging markets. It examines a comprehensive model for the effect of eWOM dimensions (including Content, Intensity, Positive Valence and Negative Valence) on the diffusion of innovations. Thus, it provides new insights on how entrepreneurial firms can use eWOM as a communication tool to facilitate the diffusion rate of innovations in emerging markets.

A quantitative approach was adopted, consisting of 215 responses from Jordan. Data were analysed using Linear regression analysis tools.

A significant relationship exists between eWOM dimensions (Content, Intensity, Positive Valence and Negative Valence) and the Diffusion Rate of Innovations. In emerging markets, eWOM content highlights critical information regarding consumers’ sentiments towards new products (including features, price, design), which consumers use in judging innovations. Especially when there is a high volume of eWOM about a new product, consumers are likely to gain reassurances regarding their purchase decisions. Specifically, the valence of eWOM (including reviews, complaints and suggestions) generate adoption/risk-aversion attitudes towards new products. Consequently, entrepreneurial firms must carefully analyse eWOM regarding their products and integrate them into their marketing strategy. 10;

This research extends the eWOM literature by developing a comprehensive model for the effect of eWOM dimensions on the diffusion of innovations. Additionally, it sheds new light on the effect of eWOM valence on consumers’ attitudes towards innovations. Finally, it provides significant theoretical and managerial implications and future research direction to deepen our understanding of the effect of eWOM on entrepreneurial firms.

The evaluation of perceived attribute performance reflected in online consumer reviews (OCRs) is critical in gaining timely marketing insights. This study proposed a text mining approach to measure consumer sentiments at the feature level and their asymmetric impacts on overall product ratings.

This study employed 49,130 OCRs generated for 14 wireless earbud products on Amazon.com. Word combinations of the major quality dimensions and related sentiment words were identified using bigram natural language processing (NLP) analysis. This study combined sentiment dictionaries and feature-related bigrams and measured feature level sentiment scores in a review. Furthermore, the authors examined the effect of feature level sentiment on product ratings.

The results indicate that customer sentiment for product features measured from text reviews significantly and asymmetrically affects the overall rating. Building upon the three-factor theory of customer satisfaction, the key quality dimensions of wireless earbuds are categorized into basic, excitement and performance factors.

This study provides a novel approach to assess customer feature level evaluation of a product and its impact on customer satisfaction based on big data analytics. By applying the suggested methodology, marketing managers can gain in-depth insights into consumer needs and reflect this knowledge in their future product or service improvement.

This study aims to compare online review characteristics, review length and review sentiment score between “organic” and “regular” food products. In addition, variations in the consumer sentiment scores across the review lengths are studied.

This study fits into the descriptive research design. From Amazon’s website, the consumer product reviews are scrapped. Using the text analytical package “sentiment” in R-Studio, we computed the sentiment scores and counted the number of words in each review. The mean sentiment scores and mean review length are compared for regular and organic products using one-way ANOVA. Sentiment score variation across review length and product class is studied through factorial ANOVA. Sample reviews of ghee and honey are used to test the hypotheses.

The review length shows a significant difference between the regular and organic products. The mean number of words in the regular products reviews is significantly lower than the mean number of words in the organic product reviews. The regular products’ mean sentiment score is significantly lower than the mean sentiment score of organic products. The mean sentiment scores are not consistent between ghee and honey. Sentiment scores are better for organic honey and regular ghee products. For regular ghee products, longer reviews result in lower sentiment scores. For regular and organic versions of honey, longer reviews are associated with better sentiment scores.

This study did not include the helpfulness of a review and the demographic data of the reviewers.

Sentiment scores’ variations across the regular and organic and product categories such as ghee and honey give a comprehensive feedback to the firms. It also indirectly communicates a brand’s evaluation by the consumers and the performance feedback for an upward extension like the organic category.

Studies on organic category give feedback for environment-friendly products and consumer attitude shift towards safer products.

Very limited studies have reported the upward line extensions. The authors study the upward line extension organic and associated sentiment scores variation. The role of review length and its systematic influence on the sentiment scores, variations in the review due to the product nature (organic/regular) are unique contributions of this study.

The purpose of this study is to illustrate the influence of media coverage and sentiment about brands on user-generated content amplification and opinions expressed in social media.

This study used a mixed-method approach, using a brand situation as a case example, including sentiment analysis of social media conversations and sentiment analysis of media coverage. This study tracks the diffusion of a false claim about the brand via online media coverage, subsequent spreading of the false claim via social media and the resulting impact on sentiment toward the brand.

The findings illustrate the influence of digital mass communication sources on the subsequent spread of information about a brand via social media channels and the impact of the social spread of false claims on brand sentiment. This study illustrates the value of social media listening and sentiment analysis for brands as an ongoing business practice.

While it has long been known that media coverage is in part subsequently diffused through individual sharing, this study reveals the potential for media sentiment to influence sentiment toward a brand. It also illustrates the potential harm brands face when false information is spread via media coverage and subsequently through social media posts and conversations. How brands can most effectively correct false brand beliefs and recover from negative sentiment related to false claims is an area for future research.

This study suggests that brands are wise to use sentiment analysis as part of their evaluation of earned media coverage from news organizations and to use social listening as an alert system and sentiment analysis to assess impact on attitudes toward the brand. These steps should become part of a brand’s social media management process.

Media are presumed to be impartial reporters of news and information. However, this study illustrated that the sentiment expressed in media coverage about a brand can be measured and diffused beyond the publications’ initial reach via social media. Advertising positioned as news must be labeled as “advertorial” to ensure that those exposed to the message understand that the message is not impartial. News organizations may inadvertently publish false claims and relay information with sentiment that is then carried via social media along with the information itself. Negative information about a brand may be more sensational and, thus, prone to social sharing, no matter how well the findings are researched or sourced.

The value of the study is its illustration of how false information and media sentiment spread via social media can ultimately affect consumer sentiment and attitude toward the brand. This study also explains the research process for social scraping and sentiment analysis.

The purpose of this paper is to use Twitter analysis to explore diner perceptions of four types of Asian restaurants (Chinese, Japanese, Korean and Thai).

Using 86,015 tweets referring to Asian restaurants, this research used text mining and sentiment analysis to find meaningful patterns, popular words and emotional states in opinions.

Twitter users held mingled perceptions of different types of Asian restaurants. Sentiment analysis and ANOVA showed that the average sentiment scores for Chinese restaurants was significantly lower than the other three Asian restaurants. While most positive tweets referred to food quality, many negative tweets suggested problems associated with service quality or food culture.

This research provides a methodology that future researchers can use in applying social media analytics to explore major issues and extract sentiment information from text messages.

Limited research has been conducted applying social media analysis in hospitality research. This study fills a gap by using social media analytics with Twitter data to examine the Twitter users’ thoughts and emotions for four different types of Asian restaurants.

The purpose of this paper is to investigate temporal tweet patterns and their effectiveness in predicting the financial performance of a movie. Specifically, how tweet patterns are formed prior to and after a movie’s release and their usefulness in predicting a movie’s success is explored.

Volume was measured and sentiment analysis was performed on a sample of Tweets posted four days before and after the release of 86 movies. The temporal pattern of tweeting for financially successful movies was compared with those that were financial disappointments. Using temporal tweet patterns, a number of machine learning models were developed and their predictive performance was compared.

Results show that the temporal patterns of tweet volume, length and sentiment differ between “hits” and “busts” in the days surrounding their releases. Compared with “busts” the tweet pattern for “hits” reveal higher volume, shorter length, and more favourable sentiment. Discriminant patterns in social media features occur days in advance of a movie’s release and can be used to develop models for predicting a movie’s success.

Analysis of temporal tweet patterns and their usefulness in predicting box office returns is the main contribution of this research. Results of this research could lead to development of analytical tools allowing motion picture studios to accurately predict and possibly influence the opening night box-office receipts prior to the release of the movie. Also, the specific temporal tweet patterns presented by this work may be applied to problems in other areas of research.

This paper aims to investigate the links between daily review sentiment and the hotel performance measures of occupancy rate (OR), average daily rate (ADR) and revenue per available room (RevPAR).

The authors conducted review sentiment analyses in three moments (−1, −7 and −14 days) before arrival time using a data set of budget hotel performance and online reviews. The aim was to identify the effect of review sentiment in the budget hotel market on the three performance metrics.

Daily sentiment positively affects ADR and negatively affects OR and RevPAR, but only up to a certain threshold, after which the trend reverses. Prices increase with the level of sentiment, and high prices lead to low OR and RevPAR only when the sentiment scores are low. When they are high, they are associated with low rates, which lead to high OR and RevPAR.

Daily review sentiment can be viewed as a valuable “barometer” indicating a hotel’s daily operational effectiveness. Daily sentiment can thus allow hotel managers to adjust their dynamic pricing strategies more accurately.

This study identifies daily sentiment as an alternative predictor of hotel performance. In addition to the roles of valence and volume in the decision-making process, the authors found that daily review sentiment can be an “in-the-moment” factor with a high impact, encouraging consumers to complete their transactions. This study suggests that aggregated measures such as the total number of reviews and overall ratings of the hotel should not be the sole consideration in reputation management.