Print Сite this

Data Mining for Predictive Social Network Analysis

Introduction

Efficient data mining requires the use of sources corresponding to the spirit of the times. In the present-day world, such sources are related to the ones that appear due to technological progress. For this paper, Twitter is appraised as a mine of information that reflects the opinions of people on every matter (Lashari & Wiil, 2016). This fact makes it useful not only for political organisations and social institutions but also for businesses that intend to increase their profits. Therefore, this paper aims to reveal the mechanism of data mining with the help of Twitter. For this, the literature on the topic is reviewed, and challenges and recommendations are presented. As a result, the overall impact of Twitter and similar platforms on the present-day companies is demonstrated.

We will write a
custom essay
specifically for you

for only $16.05 $11/page
308 certified writers online
Learn More

Literature Reviews

The analysis of Twitter implies the consideration of people’s opinions from the tweets and retweets. They include various topics, among which the feedback on the government’s policies, organisations, and companies is most crucial for the study (Lashari & Wiil, 2016). The necessity to apply an appropriate method for analysing such data makes the researchers examine new models and approaches. Thus, for example, Lashari and Will (2016) proposed a novel mechanism addressing this task that collects and processes information on specific topics based on hashtags (Lashari & Wiil, 2016). It consists of Twitter Data Fetcher, Social Network Generator, and Retweet Analyser, which, when applied consecutively, presents the process of analysing data from the platform. However, to ensure the effectiveness of such a tool, it is also critical to consider other factors.

For example, the case of the Ebola outbreak showed that spatial and social distances matter when it comes to reviewing people’s opinions. Van Lent et al. (2017) claim that public attention and sentiment expressed on Twitter was conditional upon the location of people. Even though the situation affected mostly Guinea, Sierra Leone, and Liberia, the western countries also showed the keenest concern at the issue (Van Lent et al., 2017). Nevertheless, the latter’s reaction was mild compared to the one of the citizens of countries suffering from the epidemic (Van Lent et al., 2017). This conclusion allowed to assume that distance can be used for predicting public attention in the case of worldwide crises (Van Lent et al., 2017). The same applies to any other sphere, such as politics or domestic production of goods.

The feedback of Twitter users proved to be useful in terms of the prediction of political events. The analysis of the opinions on the United States presidential election in 2016 and the candidates, Donald Trump and Hillary Clinton, is the case when researchers managed to forecast the outcome (Alshehri & Fujino, 2017). This study was based on the assumption that information systems, such as Twitter, can predict the election’s results (Alshehri & Fujino, 2017). The process consisted of gathering the public emotions, both negative and positive, on the matter and their further analysis. This way, the usefulness of Twitter for political forecasts was proved.

Another application of analysis of Twitter data proposed by the researchers relates to disaster management. The consideration of this social media platform in the context is conditional upon the fact that both public and private organisations use it to disseminate information on disasters in the world (Gunawong, Thongpapanl, & Ferreira, 2019). However, there is a difference in their politics regarding this objective. Thus, for example, public organisations, due to the presence of specific restrictions provide less information than private ones (Gunawong et al., 2019). Therefore, the decision-making process for them will include the analysis of methods to use Twitter for their goals.

In addition to applying the social media platform to the consideration of worldwide crises, epidemics, presidential elections, and natural disasters, it can also be beneficial in terms of business. Since the present-day companies strive to increase profits by all means, this source of information will be invaluable for predicting demand or customers’ attitude towards the quality of their products. Moreover, the analysis of tweets and retweets allows predicting new ventures’ success or failure (Antretter et al. 2019). In this way, such an indicator of online legitimacy plays a significant role in companies’ survival.

The Information Centre for Flood Victims and Twitter

The Information Centre for Flood Victims (ICFV), also known as “Thaiflood,” is an example of a private-led organisation adopting the methods of using Twitter for their benefit. Since private entities provide more information than the public ones, its consideration will be useful for a better understanding. This organisation aims to gather comprehensive data on floods and weather forecasts and provide support for victims of this disaster in Thailand with the help of local hospitals and clinics (Gunawong et al., 2019). For this, it widely uses Twitter as one of the main channels of information distribution.

Get your
100% original paper
on any topic

done in as little as
3 hours
Learn More

The ICFV adopted the hashtag #Thaiflood to increase the number of citizens informed on the flood situation. It became popular when news reporters in Thailand started to add it to their personal Twitter accounts (Gunawong et al., 2019). Hence, the organisation did not need to invent new tools to spread the information and just continued the initiative of news agencies and flood victims. The distinctive feature of the ICFV is the diversity of presented data, which also include recommendations for preparation for floods, warnings, and traffic conditions (Gunawong et al., 2019). Hence, the use of Twitter by this organisation proved that this platform is beneficial not only for analytics but also for informing people. Its data can be used for the consideration of the flood situation by researchers.

Operational Constraints/Challenges Faced by the ICFV

The principal operational constraints and challenges faced by the ICFV are related to the organisation’s nature. Since it is a private entity that distributes more extensive information on the country’s flood situation than the public National Disaster Warning Centre, the main issue would be the trustworthiness of data (Gunawong et al., 2019). As can be seen from the research, it focuses on specific aspects neglected by the NDWC, such as flood control efforts, relief provision, and requests for help (Gunawong et al., 2019). However, the data scope does not guarantee their quality since individuals also use the hashtag #Thaiflood. In this case, the warnings of the ICFV can be ignored by the population that tends to trust official sources.

Initiatives Adopted to Overcome These Problems

Data mining in Twitter employed by the ICFV is undoubtedly an effective mechanism of receiving and distributing information on the country’s flood situation. However, to increase its efficiency, it is vital to eliminate the problem of the untrustworthiness of the presented data and the preference of the NDWC over the ICFV. For this, the latter retweets the information from public organisations, including NDWC (Gunawong et al., 2019). Moreover, the organisation’s policies are orientated on the coverage of all events without exceptions to avoid the lack of flood data in 2013 (Gunawong et al., 2019). Hence, the combination of the cooperation with public organisations and the consideration of all cases of flooding in the country are intended to overcome the challenges.

The Impact on Organisation Productivity and Strategies

The use of tweets and retweets by analysts working for companies and worldwide organisations contributes to increased productivity and efficiency. Moreover, the process is bilateral since the entities such as both the ICFV and Tweeter users benefit from the reception of information from this social media platform. First, it allows predicting the outcome of a new venture’s business operations for five years (Antretter et al., 2019). Such a measure ensures the company’s survival and presents the ground for its further strategies of sustainable development.

Second, network analysis based on tweets and retweets performed in an organisation’s setting provides a clear picture of stakeholders’ interests and perceptions related to its daily activity. In this way, these entities can benefit from the increase in flexibility conditional upon people’s attitudes. The efficiency of their work will be improved through the application of the received data to the current strategies and elaboration of new initiatives intended to ensure the growth of organisations and companies. Hence, business plans incorporating the feedback of Twitter users will be more efficient and flexible, which is vital for further development.

Competitive Strategy and Social and Economic Networks

The use of data from social networks by companies is beneficial not only in terms of increasing the efficiency of their business operations but also for ensuring their competitiveness on the market. These information sources, one of which is Twitter, present invaluable insights about the popularity of products (Antretter et al., 2019). Moreover, they serve as the tools that can be used by marketers to draw attention to the offers of a company and thereby enhance their attractiveness to the customers.

This way, competitive strategies can be based on the comparison of one’s products and their representation on the platform with the products of other companies. Such an initiative implies the orientation of marketers’ work on the average needs of the market as well as the methods of others to address them. It can be complemented by the engagement of the company’s representatives in online communication with customers allowing to maximize its impact and improve the image among them.

We will write a custom
essays
specifically
for you!
Get your first paper with
15% OFF
Learn More

Network Analysis of the Findings

The overall impact of Twitter on social and economic networks can be presented in detail by considering its aspects with the help of network analysis concepts. Thus, the actors in the process are companies and organisations that benefit from the information received from tweets as well as posted on the platform and people using it. The relationships between them are defined through the continuous need for data allowing the former to readjust their policies to the customers’ needs and the latter to receive extensive information on the matter. In this case, the actors can be combined into groups, such as the marketing department.

These concepts are complemented by the subgroup of individuals with personal accounts that provide companies with data on the current events in the business world or natural disasters, as in the case of ICFV. They also include brokers that connect the companies or organisations and their customers presented by marketers and local news reporters. In this way, the social network created based on Twitter includes all entities and individuals with similar interests connected by the specialists whose work implies the processing of information posted by the two sides.

Recommendations for the United Arab Emirates

The adoption of such approaches as the analysis of tweets and retweets on specific topics by organisations within the United Arab Emirates is conditional upon the use of an appropriate model. The technique proposed by Lashari and Wiil (2016) can be used as the ground for further research and the consequent practical implementation in the setting of UAE markets. Hence, the principal task is to adopt the method for monitoring public opinions through measuring the sentiment of retweets on Twitter. It will be beneficial for any kind of organisations and companies as well as individuals in the country.

The second stage is the creation of social networks based on organisations involved in forecasting natural disasters, such as floods, landslides, or earthquakes. In this situation, the experience of the ICFV and the NDWC can be borrowed (Gunawong et al., 2019). The adoption of the scheme allowing to receive reliable information for the analysis of events and distribute its results through Twitter accounts will be the best option. However, this measure should be complemented by the development of cooperation between organisations with similar objectives to ensure shared data’s trustworthiness and, therefore, their good reputation.

The third stage of the project related to the creation of social networks based on Twitter accounts should be the adoption of the practices mentioned above by the UAE’s new ventures. This measure will increase the probability of their future success and sustainable development. In this way, the country’s economy will significantly benefit from the efficiency of its companies on the market. This initiative should be implemented with regard to the principles of measuring the online legitimacy of the Twitter content and the machine learning approach presented above.

The final stage of the initiative on the establishment of a social network on Twitter is the spread of the practice from the first companies involved in it to the others. In this way, the former will present the benefits of this approach in terms of increasing profits and ensuring the sustainable development of businesses in the United Arab Emirates. It will encourage other companies to join the project and thereby benefit from the social network of companies and customers on Twitter. Moreover, the involvement of a greater number of businesses will allow individuals to gain a better understanding of such entities’ daily operations and visions for the future.

Conclusion

To sum up, Twitter as a source of information can be extremely useful for predictions in politics, natural disasters, and businesses. It has a tremendous impact on present-day companies and organisations by providing them with extensive data to readjust their policies according to the world’s needs. The experience of such entities as the ICFV and the NDWC can be borrowed by the ventures of the United Arab Emirates for their benefit. However, to make this process efficient, it would be vital to consider all types of companies and organisations and focus on the analysis of tweets for their particular objectives.

References

Alshehri, M., & Fujino, I. (2017). Who will win? Donald Trump or Hillary Clinton forecast the winner of presidential election from public emotion in Twitter. 東海大学紀要. 情報通信学部, 10(1), 74-77.

Need a
100% original paper
written from scratch

by professional
specifically for you?
308 certified writers online
Learn More

Antretter, T., Blohm, I., Grichnik, D., & Wincent, J. (2019). Predicting new venture survival: A Twitter-based machine learning approach to measuring online legitimacy. Journal of Business Venturing Insights, 11.

Gunawong, P., Thongpapanl, N., & Ferreira, C. C. (2019). A comparative study of Twitter utilization in disaster management between public and private organisations. Journal of Public Affairs, 19(4).

Lashari, I. A., & Wiil, U. K. (2016, July). Monitoring public opinion by measuring the sentiment of retweets on Twitter. In 3rd European Conference on Social Media (pp. 153-161). Academic Conferences and Publishing International.

Van Lent, L. G., Sungur, H., Kunneman, F. A., Van De Velde, B., & Das, E. (2017). Too far to care? Measuring public attention and fear for Ebola using Twitter. Journal of Medical Internet Research, 19(6).

Cite this paper

Select style

Reference

StudyCorgi. (2022, June 20). Data Mining for Predictive Social Network Analysis. Retrieved from https://studycorgi.com/data-mining-for-predictive-social-network-analysis/

Reference

StudyCorgi. (2022, June 20). Data Mining for Predictive Social Network Analysis. https://studycorgi.com/data-mining-for-predictive-social-network-analysis/

Work Cited

"Data Mining for Predictive Social Network Analysis." StudyCorgi, 20 June 2022, studycorgi.com/data-mining-for-predictive-social-network-analysis/.

* Hyperlink the URL after pasting it to your document

1. StudyCorgi. "Data Mining for Predictive Social Network Analysis." June 20, 2022. https://studycorgi.com/data-mining-for-predictive-social-network-analysis/.


Bibliography


StudyCorgi. "Data Mining for Predictive Social Network Analysis." June 20, 2022. https://studycorgi.com/data-mining-for-predictive-social-network-analysis/.

References

StudyCorgi. 2022. "Data Mining for Predictive Social Network Analysis." June 20, 2022. https://studycorgi.com/data-mining-for-predictive-social-network-analysis/.

References

StudyCorgi. (2022) 'Data Mining for Predictive Social Network Analysis'. 20 June.

This paper was written and submitted to our database by a student to assist your with your own studies. You are free to use it to write your own assignment, however you must reference it properly.

If you are the original creator of this paper and no longer wish to have it published on StudyCorgi, request the removal.