Social Media Benefits for Crowdsourcing Systems

Crowdsourcing is a process of acquisition, integration, and analysis of numerous heterogeneous data, which generated from diverse sources. Social media data not only provides mass volume of data, real-time monitoring and large scale of analysis. But it also plays an important role in many disciplines. Crowdsourcing with social media data have been applied in many disciplines.

Introduction

Human computation projects include work on crowdsourcing, where people from worldwide can jointly contribute to the solution of problems. Crowdsourcing systems have emerged as a strong alternative to data collection and processing problems in the last two decades. Kaplan and Haenlein define social media “as a group of Internet-based applications that build on the ideological and technological foundations of Web 2.0, and that allow the creation and exchange of user-generated content.” There are an increasing number of organizations pay more attention to how social media can be used to contribute their crowdsourcing campaigns.

Key Concepts

A well defined concept for crowdsourcing is that: it is the distribution of tasks to large groups of individuals via a flexible, open call. It has created messes of opportunities to advance science through the efficient allocation of labor to generate, collect, clean, and transform data. The crowdsourcing approach is useful in overcoming budget, equipment and scale limitations that would otherwise limit the scope of projects in their ability to collect or process data, by offloading the work from researchers and practitioners to members of the general public.

Generally, crowdsourcing projects sorting into three categories: data augmenting, data processing and innovation generation. Garcia-Molina et al. states that while data augmenting, people are excel at collecting data where the request is not so well formed (e.g., we need something for trimming nose hair), the data needs to be latest (e.g., what is the current wait time at a given restaurant), or the data reflects human judgment or opinion (e.g., what are good movies to watch on NetFlix this weekend). In data processing, the participants are are much better handling image analysis, understanding natural language, and other involve sophisticated judgment tasks than machine. lastly, innovation generation required a process of co-creation to find optimal solutions to existing problems. Usually in a competitive approach.

Because of developed technology that most users are using smartphone as 24/7 companies today, that makes social media an important role to interact between customers and companies. Initially, social media was created to be served for communication, sharing content and decreasing the physical distance between users. Kaplan and Haenlein define social media “as a group of Internet-based applications that build on the ideological and technological foundations of Web 2.0, and that allow the creation and exchange of user-generated content.” Social media contains blogs, web pages, networking sites, and forums to allow interaction and communication among participants. Social media not only easing collaboration with different parties through better communication, but also creating values by building truthful relationship between users and companies.

How Beneficial is Social Media for Crowdsourcing Systems?

Prodanova and Van indicated that social media may provide more diverse opportunities to companies, such as crowdsourcing and gamification. There is a very rapid growth in the analysis of data from social media and social networking sites, Twitter and Flickr are being most frequently used as data sources in environmental research. Social media data offer unprecedented opportunities in terms of data volume, scale of analysis, and real-time monitoring. Michael Marchionda mentioned that social media is becoming an essential part to crowdsourcing as it lets organizations to rapidly reach a wider audience, cheaper and more efficiently, it also obtains a higher number of contributions, in theory leading to a better quality idea, service or innovation.

Existing Solutions

Crowdsourcing with social media data have been applied in many disciplines, such as business, health, geospatial (usually execute on mobile phone), universities, government agencies, NGOs, human computation (where people performance better than a computer, e.g.: image analysis, understanding natural language and other sophisticated judgment), events (e.g.: urban emergency event, natural disaster detection etc.).

Combining crowdworkers with machine learning that help to separate signal from noise by identified different labeling. It let researchers get health trends in real-time from public social media content continuously. The system can automate the whole workflow from data collection, filtering, labeling and training of machine learning classifier.

The Crowdbreaks’ algorithms will be improved continuously as more labeled data can be gathered from the updating tweets. Google Flu Trends (GFT) can be a suitable example to explain it. GFT is one of the most well-known flu surveillance systems that launched in 2008, but the model of GFT was updated in 2009, 2013 and 2014 in order to improve the performance. However, the model's performance decreased again and now it was discontinued.

Burger et al. indicated that some of the existing solutions “have not been able to fully take advantage of the increasingly available sources of new data generated by the proliferation of Internet technologies and mobile devices (e.g., social media, volunteered geographical information, digital news, open data, etc.).” Therefore, how to optimal use of the data should be considered in the future. At the same time, hybrid models could be seen as further direction for disease prediction projects and how to preciser the understanding of the content should also be takes into counted. In addition, a temporal bias may occur due to participants may contribute only at certain times when they are able to do it. How to adapt current incentive mechanism so temporal bias can be avoided, will be worth to investigate later.

Ghermandi and Sinclair highlight the five key areas: “integration of different types of information in data mashups, development of quality assurance procedures and ethical codes, improved integration with existing methods, and assurance of long-term, free and easy-to-access provision of public social media data” will be the critical areas for future researchers. They also mentioned that researchers are focusing on the challenges of data’s heterogeneity and noise levels, potential biases, ethics of data acquisition and use, and uncertainty about future data availability.

Conclusion

Crowdsourcing systems have emerged as a strong alternative to data collection and processing problems in the last two decades. Ghermandi and Sinclair revealed that social media data not only provides mass volume of data, real-time monitoring and large scale of analysis. But it also plays an important role in many disciplines. What is more, it offers the promise of novel tools and previously unavailable dimensions on which to test theories and search for empirical evidence. Overall, crowdsourcing and social media displayed exciting avenues and challenges in many directions.

References

• Burger, A., Oz, T., Kennedy, W.G. and Crooks, A.T.: Computational Social Science of Disasters: Opportunities and Challenges. Future Internet, 11(5), p.103. (2019)
• Garcia-Molina, H., Joglekar, M., Marcus, A., Parameswaran, A. and Verroios, V.: Challenges in data crowdsourcing. IEEE Transactions on Knowledge and Data Engineering, 28(4), pp.901-911. (2016)
• Ghermandi, A. and Sinclair, M.: Passive crowdsourcing of social media in environmental research: A systematic map. Global environmental change, 55, pp.36-47. (2019)
• Kamar, E., Hacker, S. and Horvitz, E.: Combining human and machine intelligence in large-scale crowdsourcing. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems-Volume 1 (pp. 467-474). International Foundation for Autonomous Agents and Multiagent Systems. (2012)
• Kaplan, A.M. and Haenlein, M.: Users of the world, unite! The challenges and opportunities of Social Media. Business horizons, 53(1), pp.59-68. (2010)
• Komninos, A.: Pro-social behaviour in crowdsourcing systems: Experiences from a field deployment for beach monitoring. International Journal of Human-Computer Studies, 124, pp.93-115. (2019)
• Lintott, C. and Reed, J.: Human computation in citizen science. In Handbook of human computation (pp. 153-162). Springer, New York, NY. (2013)
• Mangold, W.G. and Faulds, D.J.: Social media: The new hybrid element of the promotion mix. Business horizons, 52(4), pp.357-365. (2009)
• Müller, M.M. and Salathé, M.: Crowdbreaks: Tracking Health Trends Using Public Social Media Data and Crowdsourcing. Frontiers in public health, 7. (2019)
• Paniagua, J. and Korzynski, P.: Social Media Crowdsourcing. Encyclopedia of Creativity, Invention, Innovation and Entrepreneurship, pp.1-4. (2017)
• Prodanova, J. and Van Looy, A.: How Beneficial is Social Media for Business Process Management? A Systematic Literature Review. IEEE Access, 7, pp.39583-39599. (2019)
• Ranard, B.L., Ha, Y.P., Meisel, Z.F., Asch, D.A., Hill, S.S., Becker, L.B., Seymour, A.K. and Merchant, R.M.: Crowdsourcing—harnessing the masses to advance health and medicine, a systematic review. Journal of general internal medicine, 29(1), pp.187-203. (2014)
• Widmer, G. and Kubat, M.: Learning in the presence of concept drift and hidden contexts. Machine learning, 23(1), pp.69-101. (1996)
• Voinov, A., Kolagani, N., McCall, M.K., Glynn, P.D., Kragt, M.E., Ostermann, F.O., Pierce, S.A. and Ramu, P.: Modelling with stakeholders–next generation. Environmental Modelling & Software, 77, pp.196-220. (2016)
• Xu, Z., Liu, Y., Yen, N., Mei, L., Luo, X., Wei, X. and Hu, C.: Crowdsourcing based description of urban emergency events using social media big data. IEEE Transactions on Cloud Computing. (2016)
• Zamora, W., Calafate, C.T., Cano, J.C. and Manzoni, P.: A survey on smartphone-based crowdsensing solutions. Mobile Information Systems. (2016)
• Michael Marchionda, n.d., Crowdsourcing Spreading like Wildfire with Social Media. Available at: https://www.prescientdigital.com/articles/web-2.0/crowdsourcing-spreading-like-wildfire-with-social-media (accessed: 18 November 2019).