Computational Communication Research

Keywords

Social media analytics, mobile media analytics, financial media analytics, darknet analytics, cryptocurrency, computational advertising, health informatics, analytics of physiological data, etc.

Research Interests

Computational communication research employs computational methods such as user log analytics, text mining, online experiment, network analysis, and etc. to address both long-standing and emerging questions that bear either theoretical or applicational importance in media and communication. As the name suggests, it is an interdisciplinary approach across communication, computer science, data science, management science, physical science, engineering, and many neighboring social sciences. The following is a partial list of ongoing projects undertaken by members of the clusters with funding support from GRF, PPR, ITC, NSSFC, and other sources.

• Interplay among media coverage, public opinion, and government policy during the COVID19 outbreak. The project aims to track and evaluate how the media, the public, and the government around the world interact with each other about and react to COVID19. The findings are expected to help prepare the society worldwide to cope with major public health crises in the future.
• Transmission of misinformation during the COVID19 outbreak. The project aims to track and evaluate how misinformation spreads across social media in times of the pandemic outbreak. The findings are expected to enhance understanding of misinformation dissemination and help organizations and communicators to find ways to counteract misinformation during the public health crises.
• Knowledge graph of social media research. The project aims to construct a knowledge graph of conceptual ontology and empirical findings of social media research, based on the latest techniques of natural language processing and deep learning. The resulting knowledge graph is expected to serve scholarly syntheses and practical applications of empirical social media studies.
• Social media analytics for financial market surveillance. The project aims to use AI-driven technology and social media big data to develop and deploy a set of intelligence systems to monitor financial environment in Hong Kong and beyond. The resulting systems is expected to help financial industry, government regulators, and the general consumers to keep abreast of the rapid changing financial ecosystems.
• Darknet and cryptocurrency analytics. The project centers around the mining of behavior patterns of darknet and cryptocurrency users. The findings are expected to help fight against drug abuse, Internet crimes and financial frauds.
• Message framing in communication. The project examines the effects of message framing in communication to support decision-making involving risk and uncertainty.
• Using physiological data to interpret communication and infer user cognitive and emotional states. The project examines the use of physiological data to understand user cognitive and emotional states in computer-mediated communication.

Recent Publications

I. Journal Articles:

Huang, G., & Liang, H. (2021). Uncovering the effects of textual features on trustworthiness of online consumer reviews: A computational-experimental approach. Journal of Business Research, 126, 1-11. https://doi.org/10.1016/j.jbusres.2020.12.052

Chen, Z., Jardine, E., & Liu, X. F. & Zhu, J. J. H. (in press). Seeking Anonymity on the Internet: The Knowledge Accumulation Process and Global Usage of the Tor Network. New Media & Society.

Liu, X. F., Ren, H-H., Liu, S-H., & Jiang, X-J. (2021). Characterizing key agents in the cryptocurrency economy through blockchain transaction analysis. EPJ Data Science, 10, [21]. https://doi.org/10.1140/epjds/s13688-021-00276-9

Jiang, X-J., & Liu, X. F. (2021). CryptoKitties Transaction Network Analysis: The Rise and Fall of the First Blockchain Game Mania. Frontiers in Physics, 9, [631665]. https://doi.org/10.3389/fphy.2021.631665

Sharma, K., Zhan, X., Nah, F., Siau, K., and Cheng, M., “Impact of Digital Nudging on Information Security Behavior: An Experimental Study on Framing and Priming in Cybersecurity,” Organizational Cybersecurity Journal: Practice, Process and People, Vol. 1, No. 1, September 2021, pp. 69-91.

Jia, F., Shi, Y., Sia, C., Tan, C.-H., Nah, F., and Siau, K., “Users’ Reception of Product Recommendations: Analyses Based on Eye Tracking Data,” Lecture Notes in Computer Science 12783, F. F.-H. Nah, and K. Siau (editors), Springer, 2021, pp. 90-104.

Wang, X., Song, Y., & Su, Y. (in press). Less fragmented but highly centralized: A bibliometric analysis of research in computational social science. Social Science Computer Review.

Zhao, X. & Wang, X. (in press). Dynamics of networked framing: Automated frame analysis of government media and the public on Weibo with pandemic big data. Journalism & Mass Communication Quarterly.

Bodaghi, A., Oliveira, J., & Zhu, J. J. H. (2021). The fake news graph analyzer: An open-source software for characterizing spreaders in large diffusion graphs. Software Impacts. doi: https://doi.org/10.1016/j.simpa.2021.100182.

Hou, L., Pan, Y. L., & Zhu, J. J. H. (2021). Impact of scientific, economic, geopolitical, and cultural factors on international research collaboration. Journal of Informetrics, 15(3), 101194. doi: 10.1016/j.joi.2021.101194.

Guan, L., Zhang, Y. F., & Zhu, J. J. H. (2021). Predicting information exposure and continuous consumption: Self-level interest similarity, peer-level interest similarity, and global popularity. Online Information Review. doi: 10.1108/OIR-10-2020-0475.

Zhang, Y. F., Wang, L., Zhu, J. J. H., Wang, X. F., & Pentland, A. S. (2021). The strength of structural diversity in online social networks. Research, 2021, 9831621. doi: 10.34133/2021/9831621.

Wang, C. J., & Zhu, J. J. H. (2021). Jumping over the network threshold of information diffusion: Testing the threshold hypothesis of social influence. Internet Research. doi: 10.1108/INTR-08-2019-0313.

Zhang, Y. F., Wang, L., Zhu, J. J. H., & Wang, X. F. (2021). Conspiracy vs science: A large-scale analysis of online discussion cascades. World Wide Web-Internet and Web Information Systems, 24(2), 585-606. doi: 0.1007/s11280-021-00862-x.

Peng, T. Q., Zhou, Y. X., & Zhu, J. J. H. (2020). From filled to empty time intervals: Quantifying online behaviors with digital traces. Communication Methods and Measures, 14(4), 219-238. doi: 10.1080/19312458.2020.1812556.

Zhang, Y. F., Wang, L., Zhu, J. J. H., & Wang, X. F. (2020). Viral vs broadcast: Characterizing the virality and growth of cascades. EPL, 131(2), 28002. doi:10.1209/0295-5075/131/28002.

Peng, T. Q., & Zhu, J. J. H. (2020). Mobile phone use as sequential processes: From discrete behaviors to sessions of behaviors and trajectories of sessions. Journal of Computer-Mediated Communication, 25(2), 129-146. doi:10.1093/jcmc/zmz029.

II. Conference Papers:

Sun, W.-J., Liu, X. F., & Shen, F. (2021) Learning Dynamic User Interactions for Online Forum Commenting Prediction. In 2021 IEEE International Conference on Data Mining (ICDM), December 7-10, 2021, Auckland, New Zealand.

Zhou, Y. X., & Zhu, J. J. H. (2021). The impact of digital media on daily rhythms: Intrapersonal diversification and interpersonal differentiation. In the 71th annual conference of International Communication Association, online, May.

Zhou, Y. X., & Zhu, J. J. H. (2021). The temporal aspects of daily life: Their sequential mediating role in digital media’s effect on well-being. In the 71th annual conference of International Communication Association, online, May.

Zhou, Y. X., & Zhu, J. J. H. (2021). Digital media and the postmodern transformation: The daily rhythm of digital media use across 15 years. In the 71th annual conference of International Communication Association, online, May.

III. Other publications:

張倫、彭泰權(quán)、王成軍、梁海、祝建華 (2021).從邊陲到主流的一種自然路徑:華人計(jì)算傳播學(xué)者的參與和體驗(yàn).載於李立峯、黃煜（編），《中華傳播研究的傳承與創(chuàng)新》，香港中文大學(xué)出版社，399-419頁(yè)。

IV. Grants:

Huang, G. Collaborative Research Fund, the Research Grants Council (Hong Kong), “(Mis)communication, trust, and information environments: A comparative study of the COVID-19 ‘infodemics’ in four Chinese societies,” 2021-2023, Co-Principal Investigator, HKD3,067,301, On-going.

Liu, X. F. The Grand Challenges ICODA COVID-19 Data Science pilot initiative (~USD 70,000). Principal Invesgator.