Web mining for the mayoral election prediction in Taiwan

2017 ◽  
Vol 69 (6) ◽  
pp. 688-701 ◽  
Author(s):  
Jia-Yen Huang
Keyword(s):  
Social Media ◽  
Web Mining ◽  
Semantic Analysis ◽  
Transport Infrastructure ◽  
Content Type ◽  
Part Of Speech ◽  
Phrase Extraction ◽  
Mayoral Election ◽  
Election Prediction ◽  
Election Results

Purpose The prediction of pre-election polls is an issue of concern for both politicians and voters. The Taiwan nine-in-one election held in 2014 ended with jaw-dropping results; apparently, traditional polls did not work well. As a remedy to this problem, the purpose of this paper is to utilize the comments posted on social media to analyze civilians’ views on the two candidates for mayor of Taichung City, Chih-chiang Hu, and Chia-Lung Lin. Design/methodology/approach After conducting word segmentation and part-of-speech tagging for the collected reviews, this study constructs the opinion phrase extraction rules for identifying the opinion words associated with the attribute words. Next, this study classifies the attribute words into six municipal governance-related topics and calculates the opinion scores for each candidate. Finally, this study uses correspondence analysis to transform opinion information on the candidates into a graphical display to facilitate the interpretation of voters’ views. Findings The results show that the topics of candidates’ backgrounds and transport infrastructure were the two most critical factors for the election prediction. Based on the predication, Lin outscores Hu by 17.74 percent which is close to the real election results. Research limitations/implications This study proposes new rules for the extraction of Chinese opinion words associated with attribute words. Practical implications This study applies Chinese semantic analysis to assist in predicting election results and investigating the topics of concern to voters. Originality/value The proposed opinion phrase extraction rules for Chinese social media, as well as the election forecast process, can provide valuable references for political parties and candidates to plan better nomination and election strategies.

US poll security will likely still be issue in 2020

2019 ◽  
Keyword(s):  
Social Media ◽  
Presidential Election ◽  
Content Type ◽  
Public Pressure ◽  
Election Results ◽  
Election Systems ◽  
Media Firms

Significance The bill will move to the Senate, where Republicans fear it over-reaches into states’ powers to manage elections. The standoff takes place within the context of the aftermath of the 2016 presidential election, in which Russians interfered via informational techniques and social media. The bill is designed to prevent another such occurrence, but the ability for actors to manipulate election results is more far-reaching than the methods addressed in this bill. Impacts The bill would authorise federal money annually to improve and maintain states’ election systems. Social media firms will face more government and public pressure to prevent foreign election interference via their platforms. Social media firms will find it difficult to police their platforms without increasing editorial control.

scholarly journals Influential spreaders in the political Twitter sphere of the 2013 Malaysian general election

2019 ◽  
Vol 119 (1) ◽  
pp. 54-68 ◽  
Author(s):  
Hong-liang Sun ◽  
Eugene Ch’ng ◽  
Simon See
Keyword(s):  
Social Media ◽  
Political Parties ◽  
General Election ◽  
The Political ◽  
Content Type ◽  
Political Sphere ◽  
Before And After ◽  
Election Results ◽  
New Perspective ◽  
Propagation Network

Purpose The purpose of this paper is to investigate political influential spreaders in Twitter at the juncture before and after the Malaysian General Election in 2013 (MGE2013) for the purpose of understanding if the political sphere within Twitter reflects the intentions, popularity and influence of political figures in the year in which Malaysia has its first “social media election.” Design/methodology/approach A Big Data approach was used for acquiring a series of longitudinal data sets during the election period. The work differs from existing methods focusing on the general statistics of the number of followers, supporters, sentiment analysis, etc. A retweeting network has been extracted from tweets and retweets and has been mapped to a novel information flow and propagation network we developed. The authors conducted quantitative studies using k-shell decomposition, which enables the construction of a quantitative Twitter political propagation sphere where members posited at the core areas are more influential than those in the outer circles and periphery. Findings The authors conducted a comparative study of the influential members of Twitter political propagation sphere on the election day and the day after. The authors found that representatives of political parties which are located at the center of the propagation network are winners of the presidential election. This may indicate that influential power within Twitter is positively related to the final election results, at least in MGE2013. Furthermore, a number of non-politicians located at the center of the propagation network also significantly influenced the election. Research limitations/implications This research is based on a large electoral campaign in a specific election period, and within a predefined nation. While the result is significant and meaningful, more case studies are needed for generalized application for identifying potential winning candidates in future social-media fueled political elections. Practical implications The authors presented a simple yet effective model for identifying influential spreaders in the Twitter political sphere. The application of the authors’ approach yielded the conclusion that online “coreness” score has significant influence to the final offline electoral results. This presents great opportunities for applying the novel methodology in the upcoming Malaysian General Election in 2018. The discovery presented here can be used for understanding how different players of political parties engage themselves in the election game in Twitter. The approach can also be adopted as a factor of influence for offline electoral activities. The conception of a quantitative approach in electoral results greatly influenced by social media means that comparative studies could be made in future elections. Originality/value Existing works related to general elections of various nations have either bypassed or ignored the subtle links between online and offline influential propagations. The modeling of influence from social media using a longitudinal and multilayered approach is also rarely studied. This simple yet effective method provides a new perspective of practice for understanding how different players behave and mutually shape each other over time in the election game.

COVID-19 and repression will fuel new African protests

2020 ◽  
Keyword(s):  
Social Media ◽  
Content Type ◽  
Election Results ◽  
At Home

Significance This has led to a greater focus on digital strategies and the rise of ‘personal’ or ‘patchwork’ protests in which individuals share images on social media of themselves making personal statements at home. Some of these efforts, such as the ‘bush protest’ in Zambia and the ‘#ZimbabweanLivesMatter’ movement, have gone viral, trending globally. Impacts The growing focus and engagement in digital forms of protest will see authoritarian leaders increase their efforts to control these spaces. Already over-extended Western donors will be reluctant to become more involved in a range of complex democratic struggles in Africa. Online protests will frequently have more of an impact on international opinion than on domestic election results.

scholarly journals Exploring the Power of Social Media in Election Predictions

2019 ◽  
Vol 8 (2) ◽  
pp. 4539-4549
Keyword(s):  
Social Media ◽  
Economic Indicators ◽  
Prediction System ◽  
Traditional Methods ◽  
Election Forecasting ◽  
Forecasting Methods ◽  
Development Agenda ◽  
Election Prediction ◽  
Election Results ◽  
Diverse Nations

The forecasting of election’s outcome remained prevailed in prominence from pre-historic times and is still a delightful topic of the current era. The predictions of election results have been started from traditional methods to economic indicators and now is being swung by social media especially sentimental analysis. The present studies discuss the election forecasting methods carried out in diverse nations by the number of researchers till now. Furthermore, different number of approaches for electoral prediction using social media and economic dimensions has been investigated based on previous literature work. The main focus of this work is to study and examine various techniques, methods and parameters used for election predictions in distinct areas. Finally, we suggest some intelligent techniques which will be based upon some parameters such as the development agenda, party type and religionism etc for further modification in election prediction system, so as to enhance the accuracy of political forecasting globally

Motivating Exercise Through Social Media: Is a Picture Always Worth a Thousand Words?

2018 ◽  
Author(s):  
Caitlyn Johnston ◽  
William E. Davis
Keyword(s):  
Social Media ◽  
Individual Differences ◽  
Experimental Design ◽  
Health Behaviors ◽  
Media Content ◽  
Exercise Motivation ◽  
Positive Health ◽  
Content Type ◽  
Within Subjects

In the present study, we examined how the influence of exercise-related social media content on exercise motivation might differ across content type (with images vs. without images) and account type (individual vs. corporate). Using a 2 × 2 within-subjects experimental design, 229 participants viewed a series of 40 actual social media posts across the four conditions (individual posts with images, corporate posts with images, individual posts without images, and corporate posts without images) in a randomized order. Participants rated the extent to which they felt each social media post motivated them to exercise, would motivate others to exercise, and was posted for extrinsic reasons. Participants also completed other measures of individual differences including their own exercise motivation. Posts with images from individuals were more motivating than posts with images from corporations; however, corporate posts without images were more motivating than posts without images from individuals. Participants expected others to be similarly motivated by the stimuli, and perceived corporate posts as having been posted for more extrinsic reasons than individuals’ posts. These findings enhance our understanding of how social media may be used to promote positive health behaviors.

Social media engagement, service complexity, and experiential quality in US hospitals

2020 ◽  
Vol 34 (6) ◽  
pp. 833-845 ◽  
Author(s):  
Youngsu Lee ◽  
Joonhwan In ◽  
Seung Jun Lee
Keyword(s):  
Social Media ◽  
Demographic Data ◽  
Positive Association ◽  
Customer Engagement ◽  
Service Firms ◽  
Multiple Sources ◽  
Cross Sectional ◽  
Content Type ◽  
Social Media Engagement ◽  
Experiential Quality

Purpose As social media platforms become increasingly popular among service firms, many US hospitals have been using social media as a means to improve their patients’ experiences. However, little research has explored the implications of social media use within a hospital context. The purpose of this paper is to investigate a hospital’s customer engagement through social media and its association with customers’ experiential quality. Also, this study examines the role of a hospital’s service characteristics, which could shape the nature of the interactions between patients and the hospital. Design/methodology/approach Data from 669 hospitals with complete experiential quality and demographic data were collected from multiple sources of secondary data, including the rankings of social media friendly hospitals, the Hospital Compare database, the Center for Medicare and Medicaid (CMS) cost report, the CMS impact file, the Healthcare Information and Management Systems Society Analytics database and the Dartmouth Atlas of Health Care. Specifically, the authors designed the instrumental variable estimate to address the endogeneity issue. Findings The empirical results suggest a positive association between a hospital’s social media engagement and experiential quality. For hospitals with a high level of service sophistication, the association between online engagement and experiential quality becomes more salient. For hospitals offering various services, offline engagement is a critical predictor of experiential quality. Research limitations/implications A hospital with more complex services should make efforts to engage customers through social media for better patient experiences. The sample is selected from databases in the US, and the databases are cross-sectional in nature. Practical implications Not all hospitals may be better off improving the patient experience by engaging customers through social media. Therefore, practitioners should exercise caution in applying the study’s results to other contexts and in making causal inferences. Originality/value The current study delineates customer engagement through social media into online and offline customer engagement. This study is based on the theory of customer engagement and reflects the development of mobile technology. Moreover, this research may be considered as pioneering in that it considers the key characteristics of a hospital’s service operations (i.e., service complexity) when discovering the link between customers’ engagement through a hospital’s social media and experiential quality.

What makes the difference? Employee social media brand engagement

2019 ◽  
Vol 34 (7) ◽  
pp. 1459-1467 ◽  
Author(s):  
Sherese Y. Duncan ◽  
Raeesah Chohan ◽  
João José Ferreira
Keyword(s):  
Social Media ◽  
Brand Equity ◽  
Positive Emotions ◽  
Content Type ◽  
Word Use ◽  
Brand Engagement ◽  
Analytical Thinking ◽  
Industry Competition ◽  
The Difference ◽  
Business To Business

Purpose This paper aims to explore, using the employee lens of business-to-business firms, word use through brand engagement and social media interaction to understand the difference between employees who rate their employer brands highly on social media and those who don't. Design/methodology/approach We conducted a textual content analysis of posts published on the social media job evaluation site glassdoor.com. LIWC software package was used to analyze 30 of the top 200 business-to-business brands listed on Brandwatch using four variables, namely, analytical thinking, clout, authenticity and emotional tone. Findings The results show that employees who rate their employer’s brand low use significantly more words, are significantly less analytic and write with significantly more clout because they focus more on others than themselves. Employees who rate their employer’s brand highly, write with significantly more authenticity, exhibit a significantly higher tone and display far more positive emotions in their reviews. Practical implications Brand managers should treat social media data disseminated by individual stakeholders, like the variables used in this study (tone, word count, frequency), as a valuable tool for brand insight on their industry, competition and their own brand equity, now and especially over time. Originality/value This study provides acknowledgement that social media is a significant source of marketing intelligence that may improve brand equity by better understanding and managing brand engagement.

scholarly journals Social Media use and value creation in the digital landscape: a dynamic-capabilities perspective

2020 ◽  
Vol 31 (3) ◽  
pp. 313-343
Author(s):  
Aurora Garrido-Moreno ◽  
Víctor García-Morales ◽  
Stephen King ◽  
Nigel Lockett
Keyword(s):  
Social Media ◽  
Value Creation ◽  
Dynamic Capabilities ◽  
Media Use ◽  
Business Value ◽  
Customer Engagement ◽  
Social Media Use ◽  
Content Type ◽  
Social Media Tools ◽  
Dynamic Capabilities Perspective

PurposeAlthough Social Media use has become all-pervasive, previous research has failed to explain how to use Social Media tools strategically to create business value in today's increasingly digital landscapes. Adopting a dynamic capabilities perspective, this paper empirically examines the specific process through which Social Media use translates into better performance and the capabilities involved in this process.Design/methodology/approachA research model is proposed that includes both antecedents and consequences of Social Media use. Existing research was examined to derive the research hypotheses, which were tested using SEM methodology on a sample of 212 hotels.FindingsThe results show that Social Media use does not exert significant direct impact on organizational performance. Rather, the findings confirm the mediating role played by Social CRM and Customer Engagement capabilities in the value creation process.Practical implicationsThe results demonstrate how Social Media tools should be implemented and managed to generate business value in hotels. Implications yield interesting insights for hotel managersOriginality/valueThis study is a first attempt to analyze empirically the real impact of digital media technologies, particularly Social Media use, drawing on the dynamic capabilities perspective and focusing on service firms (hotels). Including the variable “Organizational Readiness” as a basic prerequisite to benefit from Social Media use enhances the study's novelty and contribution.

Sign in / Sign up

Export Citation Format

Share Document