The Impact of Sentiment Analysis on Social Media to Assess Customer Satisfaction: Case of Rwanda

2019 ◽  
Author(s):  
Marius Ngaboyamahina ◽  
Sun Yi
Keyword(s):  
Social Media ◽  
Customer Satisfaction ◽  
Sentiment Analysis ◽  
The Impact

“Actions speak louder than words”: an impact of service recovery antecedents on customer delight in quick-service restaurants

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Durgesh Agnihotri ◽  
Kushagra Kulshreshtha ◽  
Vikas Tripathi ◽  
Pallavi Chaturvedi
Keyword(s):  
Social Media ◽  
Customer Satisfaction ◽  
Structural Equation ◽  
Service Recovery ◽  
Equation Modeling ◽  
Role Clarity ◽  
Content Type ◽  
Customer Delight ◽  
Quick Service ◽  
The Impact

PurposeThe purpose of this study is to conceptualize and analyze a framework that provides greater understanding toward the impact of service recovery antecedents such as role clarity, customer service orientation, employee empowerment and employee relational behavior on customer satisfaction and customer delight in the context of quick-service restaurants (QSRs).Design/methodology/approachA self-administered questionnaire was distributed to 408 participants who had experienced service recovery efforts by leading QSRs on social media. The current paper draws upon the prevailing literature to test a series of research hypotheses through structural equation modeling.FindingsThe findings of the study have confirmed that antecedents of service recovery are good to describe customer satisfaction and customer delight in the setting of QSRs. Besides, the study provides an understanding on how monetary compensation moderates the relationship between customer delight and customer satisfaction.Practical implicationsThis study carries an understanding on how frontline employees must operate in a non-conventional and innovative way to resolve customers' issues and show commitment with truthfulness to provide excellent services to make customers feel delightful.Originality/valueThis is a unique study to understand the role of service recovery antecedents to describe customer satisfaction and customer delight in the social media environment. In addition, the results support the possibilities of implementing prompt service recovery efforts using social media.

scholarly journals A Complete VADER-Based Sentiment Analysis of Bitcoin (BTC) Tweets during the Era of COVID-19

2020 ◽  
Vol 4 (4) ◽  
pp. 33
Author(s):  
Toni Pano ◽  
Rasha Kashef
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Prediction Model ◽  
Sentiment Analysis ◽  
Significant Role ◽  
Prediction Models ◽  
Financial Sector ◽  
Research Gap ◽  
Text Preprocessing ◽  
The Impact

During the COVID-19 pandemic, many research studies have been conducted to examine the impact of the outbreak on the financial sector, especially on cryptocurrencies. Social media, such as Twitter, plays a significant role as a meaningful indicator in forecasting the Bitcoin (BTC) prices. However, there is a research gap in determining the optimal preprocessing strategy in BTC tweets to develop an accurate machine learning prediction model for bitcoin prices. This paper develops different text preprocessing strategies for correlating the sentiment scores of Twitter text with Bitcoin prices during the COVID-19 pandemic. We explore the effect of different preprocessing functions, features, and time lengths of data on the correlation results. Out of 13 strategies, we discover that splitting sentences, removing Twitter-specific tags, or their combination generally improve the correlation of sentiment scores and volume polarity scores with Bitcoin prices. The prices only correlate well with sentiment scores over shorter timespans. Selecting the optimum preprocessing strategy would prompt machine learning prediction models to achieve better accuracy as compared to the actual prices.

scholarly journals Unpacking the impact of social media analytics on customer satisfaction: do external stakeholder characteristics matter?

2020 ◽  
Vol 40 (5) ◽  
pp. 647-669 ◽  
Author(s):  
Yichuan Wang ◽  
Minhao Zhang ◽  
Ying Kei Tse ◽  
Hing Kai Chan
Keyword(s):  
Social Media ◽  
Customer Satisfaction ◽  
Customer Engagement ◽  
Primary Data ◽  
Social Media Analytics ◽  
Content Type ◽  
External Stakeholder ◽  
Business Partners ◽  
External Stakeholders ◽  
The Impact

PurposeUnderpinned by the lens of Contingency Theory (CT), the purpose of this paper is to empirically evaluate whether the impact of social media analytics (SMA) on customer satisfaction (CS) is contingent on the characteristics of different external stakeholders, including business partners (i.e. partner diversity), competitors (i.e. localised competition) and customers (i.e. customer engagement).Design/methodology/approachUsing both subjective and objective measures from multiple sources, we collected primary data from 141 hotels operating in Greece and their archival data from TripAdvisor and the Hellenic Chamber of Hotels (HCH) database to test the hypothesised relationships. Data were analysed through structural equation modelling.FindingsThis study confirms the positive association between SMA and CS, but it remains subject to the varied characteristics of external stakeholders. We find that an increase in CS due to the implementation of SMA is more pronounced for firms that (1) adopt a selective distribution strategy where a limited number of business partners are chosen for collaboration or (2) operate in a highly competitive local environment. The results further indicate that high level of customer engagement amplifies the moderating effect of partner diversity (when it is low) and localised competition (when it is high) on the SMA–CS relationship.Originality/valueThe study provides novel insights for managers on the need to consider external stakeholder characteristics when implementing SMA to enhance firms' CS, and for researchers on the value of studying SMA implementation from the CT perspective.

scholarly journals To Enhance the Impact of Deep Learning-Based Algorithms in Determining the Behavior of an Individual based on Communication on Social Media

2019 ◽  
Vol 8 (12) ◽  
pp. 4433-4435
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Social Networking Sites ◽  
Opinion Mining ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Social Media Text ◽  
The Impact

In this digitized world, the Internet has become a prominent source to glean various kinds of information. In today’s scenario, people prefer virtual reality instead of one to one communication. The Majority of the population prefers social networking sites to voice themselves through posts, blogs, comments, likes, dislikes. Their sentiments can be found/traced using opinion mining or Sentiment analysis. Sentiment analysis of social media text is a useful technique for identifying peoples’ positive, negative or neutral emotions/sentiments/opinions. Sentiment analysis has gained special attention by researchers from last few years. Traditionally many machine learning algorithms were used to implement it like navie bays, Support Vector Machine and many more. But to overcome the drawbacks of ML in terms of complex classification algorithms different deep learning-based algorithms are introduced like CNN, RNN, and HNN. In this paper, we have studied different deep learning algorithms and intended to propose a deep learning-based model to analyze the behavior of an individual using social media text. Results given by the proposed model can utilize in a range of different fields like business, education, industry, politics, psychology, security, etc.

scholarly journals Website Based E-Commerce Waste Recycling Products

2021 ◽  
Vol 1 (2) ◽  
Author(s):  
Setyorini Setyorini ◽  
Syarif Hidayatullah ◽  
Ike Kusdyah Rachmawati
Keyword(s):  
Social Media ◽  
Customer Satisfaction ◽  
Customer Service ◽  
Product Information ◽  
Waste Recycling ◽  
Waste Material ◽  
Material Resource ◽  
Bank Managers ◽  
Waste Bank ◽  
The Impact

The use of websites and social media as sales engines has begun to develop in line with the advancement of e-commerce. The waste bank is a waste material resource that can be recycled and made into a usable product whose existence has been ongoing until now but does not yet have an online promotional media that suits your needs. Creating a website that is in accordance with the intended flow of needs so that the website can make it easier for waste bank managers to widely market recycled products and reach consumers nationally. Especially at the Garbage Bank Recycling Product Gallery, Mojo Sari village, Malang Regency. The waste bank recycling e-commerce website created will be able to solve customer service problems that have been complained of. The impact is the increased level of customer satisfaction with ease of viewing product information, ease of ordering, and payment processing.

scholarly journals Evolution of corporate reputation during an evolving controversy

2019 ◽  
Vol 23 (1) ◽  
pp. 52-71 ◽  
Author(s):  
Siyoung Chung ◽  
Mark Chong ◽  
Jie Sheng Chua ◽  
Jin Cheon Na
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Sentiment Analysis ◽  
Corporate Reputation ◽  
Supervised Machine Learning ◽  
Future Research ◽  
Content Type ◽  
Twitter Users ◽  
Corporate Crisis ◽  
The Impact

PurposeThe purpose of this paper is to investigate the evolution of online sentiments toward a company (i.e. Chipotle) during a crisis, and the effects of corporate apology on those sentiments.Design/methodology/approachUsing a very large data set of tweets (i.e. over 2.6m) about Company A’s food poisoning case (2015–2016). This case was selected because it is widely known, drew attention from various stakeholders and had many dynamics (e.g. multiple outbreaks, and across different locations). This study employed a supervised machine learning approach. Its sentiment polarity classification and relevance classification consisted of five steps: sampling, labeling, tokenization, augmentation of semantic representation, and the training of supervised classifiers for relevance and sentiment prediction.FindingsThe findings show that: the overall sentiment of tweets specific to the crisis was neutral; promotions and marketing communication may not be effective in converting negative sentiments to positive sentiments; a corporate crisis drew public attention and sparked public discussion on social media; while corporate apologies had a positive effect on sentiments, the effect did not last long, as the apologies did not remove public concerns about food safety; and some Twitter users exerted a significant influence on online sentiments through their popular tweets, which were heavily retweeted among Twitter users.Research limitations/implicationsEven with multiple training sessions and the use of a voting procedure (i.e. when there was a discrepancy in the coding of a tweet), there were some tweets that could not be accurately coded for sentiment. Aspect-based sentiment analysis and deep learning algorithms can be used to address this limitation in future research. This analysis of the impact of Chipotle’s apologies on sentiment did not test for a direct relationship. Future research could use manual coding to include only specific responses to the corporate apology. There was a delay between the time social media users received the news and the time they responded to it. Time delay poses a challenge to the sentiment analysis of Twitter data, as it is difficult to interpret which peak corresponds with which incident/s. This study focused solely on Twitter, which is just one of several social media sites that had content about the crisis.Practical implicationsFirst, companies should use social media as official corporate news channels and frequently update them with any developments about the crisis, and use them proactively. Second, companies in crisis should refrain from marketing efforts. Instead, they should focus on resolving the issue at hand and not attempt to regain a favorable relationship with stakeholders right away. Third, companies can leverage video, images and humor, as well as individuals with large online social networks to increase the reach and diffusion of their messages.Originality/valueThis study is among the first to empirically investigate the dynamics of corporate reputation as it evolves during a crisis as well as the effects of corporate apology on online sentiments. It is also one of the few studies that employs sentiment analysis using a supervised machine learning method in the area of corporate reputation and communication management. In addition, it offers valuable insights to both researchers and practitioners who wish to utilize big data to understand the online perceptions and behaviors of stakeholders during a corporate crisis.

scholarly journals Diabetes on Twitter: A Sentiment Analysis

2018 ◽  
Vol 13 (3) ◽  
pp. 439-444 ◽  
Author(s):  
Elia Gabarron ◽  
Enrique Dorronzoro ◽  
Octavio Rivera-Romero ◽  
Rolf Wynn
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Text Message ◽  
Positive Association ◽  
Health Condition ◽  
Media Impact ◽  
Analysis Techniques ◽  
Negative Sentiment ◽  
Public Health Strategies ◽  
The Impact

Background: Contents published on social media have an impact on individuals and on their decision making. Knowing the sentiment toward diabetes is fundamental to understanding the impact that such information could have on people affected with this health condition and their family members. The objective of this study is to analyze the sentiment expressed in messages on diabetes posted on Twitter. Method: Tweets including one of the terms “diabetes,” “t1d,” and/or “t2d” were extracted for one week using the Twitter standard API. Only the text message and the number of followers of the users were extracted. The sentiment analysis was performed by using SentiStrength. Results: A total of 67 421 tweets were automatically extracted, of those 3.7% specifically referred to T1D; and 6.8% specifically mentioned T2D. One or more emojis were included in 7.0% of the posts. Tweets specifically mentioning T2D and that did not include emojis were significantly more negative than the tweets that included emojis (–2.22 vs −1.48, P < .001). Tweets on T1D and that included emojis were both significantly more positive and also less negative than tweets without emojis (1.71 vs 1.49 and −1.31 vs −1.50, respectively; P < .005). The number of followers had a negative association with positive sentiment strength ( r = –.023, P < .001) and a positive association with negative sentiment ( r = .016, P < .001). Conclusion: The use of sentiment analysis techniques on social media could increase our knowledge of how social media impact people with diabetes and their families and could help to improve public health strategies.

scholarly journals Public Reaction to Scientific Research via Twitter Sentiment Prediction

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Murtuza Shahzad ◽  
Hamed Alhoori
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Prediction Models ◽  
Binary Classification ◽  
Computational Social Science ◽  
Research Articles ◽  
Emotional Impact ◽  
Scientific Publications ◽  
The Public ◽  
The Impact

Abstract Purpose Social media users share their ideas, thoughts, and emotions with other users. However, it is not clear how online users would respond to new research outcomes. This study aims to predict the nature of the emotions expressed by Twitter users toward scientific publications. Additionally, we investigate what features of the research articles help in such prediction. Identifying the sentiments of research articles on social media will help scientists gauge a new societal impact of their research articles. Design/methodology/approach Several tools are used for sentiment analysis, so we applied five sentiment analysis tools to check which are suitable for capturing a tweet's sentiment value and decided to use NLTK VADER and TextBlob. We segregated the sentiment value into negative, positive, and neutral. We measure the mean and median of tweets’ sentiment value for research articles with more than one tweet. We next built machine learning models to predict the sentiments of tweets related to scientific publications and investigated the essential features that controlled the prediction models. Findings We found that the most important feature in all the models was the sentiment of the research article title followed by the author count. We observed that the tree-based models performed better than other classification models, with Random Forest achieving 89% accuracy for binary classification and 73% accuracy for three-label classification. Research limitations In this research, we used state-of-the-art sentiment analysis libraries. However, these libraries might vary at times in their sentiment prediction behavior. Tweet sentiment may be influenced by a multitude of circumstances and is not always immediately tied to the paper's details. In the future, we intend to broaden the scope of our research by employing word2vec models. Practical implications Many studies have focused on understanding the impact of science on scientists or how science communicators can improve their outcomes. Research in this area has relied on fewer and more limited measures, such as citations and user studies with small datasets. There is currently a critical need to find novel methods to quantify and evaluate the broader impact of research. This study will help scientists better comprehend the emotional impact of their work. Additionally, the value of understanding the public's interest and reactions helps science communicators identify effective ways to engage with the public and build positive connections between scientific communities and the public. Originality/value This study will extend work on public engagement with science, sociology of science, and computational social science. It will enable researchers to identify areas in which there is a gap between public and expert understanding and provide strategies by which this gap can be bridged.

scholarly journals Using Social Media Data to Understand the Impact of Promotional Information on Laypeople�s Discussions: A Case Study of Lynch Syndrome (Preprint)

2017 ◽  
Author(s):  
Jiang Bian ◽  
Yunpeng Zhao ◽  
Ramzi G Salloum ◽  
Yi Guo ◽  
Mo Wang ◽  
...  
Keyword(s):  
Social Media ◽  
Colon Cancer ◽  
Genetic Testing ◽  
Lynch Syndrome ◽  
Sentiment Analysis ◽  
Health Information ◽  
Topic Modeling ◽  
Cancer Awareness ◽  
Related Information ◽  
The Impact

BACKGROUND Social media is being used by various stakeholders among pharmaceutical companies, government agencies, health care organizations, professionals, and news media as a way of engaging audiences to raise disease awareness and ultimately to improve public health. Nevertheless, it is unclear what effects this health information has on laypeople. OBJECTIVE This study aimed to provide a detailed examination of how promotional health information related to Lynch syndrome impacts laypeople’s discussions on a social media platform (Twitter) in terms of topic awareness and attitudes. METHODS We used topic modeling and sentiment analysis techniques on Lynch syndrome–related tweets to answer the following research questions (RQs): (1) what are the most discussed topics in Lynch syndrome–related tweets?; (2) how promotional Lynch syndrome–related information on Twitter affects laypeople’s discussions?; and (3) what impact do the Lynch syndrome awareness activities in the Colon Cancer Awareness Month and Lynch Syndrome Awareness Day have on laypeople’s discussions and their attitudes? In particular, we used a set of keywords to collect Lynch syndrome–related tweets from October 26, 2016 to August 11, 2017 (289 days) through the Twitter public search application programming interface (API). We experimented with two different classification methods to categorize tweets into the following three classes: (1) irrelevant, (2) promotional health information, and (3) laypeople’s discussions. We applied a topic modeling method to discover the themes in these Lynch syndrome–related tweets and conducted sentiment analysis on each layperson’s tweet to gauge the writer’s attitude (ie, positive, negative, and neutral) toward Lynch syndrome. The topic modeling and sentiment analysis results were elaborated to answer the three RQs. RESULTS Of all tweets (N=16,667), 87.38% (14,564/16,667) were related to Lynch syndrome. Of the Lynch syndrome–related tweets, 81.43% (11,860/14,564) were classified as promotional and 18.57% (2704/14,564) were classified as laypeople’s discussions. The most discussed themes were treatment (n=4080) and genetic testing (n=3073). We found that the topic distributions in laypeople’s discussions were similar to the distributions in promotional Lynch syndrome–related information. Furthermore, most people had a positive attitude when discussing Lynch syndrome. The proportion of negative tweets was 3.51%. Within each topic, treatment (16.67%) and genetic testing (5.60%) had more negative tweets compared with other topics. When comparing monthly trends, laypeople’s discussions had a strong correlation with promotional Lynch syndrome–related information on awareness (r=.98, P<.001), while there were moderate correlations on screening (r=.602, P=.05), genetic testing (r=.624, P=.04), treatment (r=.69, P=.02), and risk (r=.66, P=.03). We also discovered that the Colon Cancer Awareness Month (March 2017) and the Lynch Syndrome Awareness Day (March 22, 2017) had significant positive impacts on laypeople’s discussions and their attitudes. CONCLUSIONS There is evidence that participative social media platforms, namely Twitter, offer unique opportunities to inform cancer communication surveillance and to explore the mechanisms by which these new communication media affect individual health behavior and population health.

Sign in / Sign up

Export Citation Format

Share Document