Abstract
Collective emotion has been traditionally evaluated by questionnaire survey on a limited number of people. Recently, big data of written texts on the Internet has been available for analyzing collective emotion for very large scales. Although short-term reflection between collective emotion and real social phenomena has been widely studied, long-term dynamics of collective emotion has not been studied so far due to the lack of long persistent data sets. In this study, we extracted collective emotion over a 10-year period from 3.6 billion Japanese blog articles. Firstly, we find that collective emotion shows clear periodic cycles, i.e., weekly and seasonal behaviors, accompanied with pulses caused by natural disasters. For example, April is represented by high Tension, probably due to starting school in Japan. We also identified long-term memory in the collective emotion that is characterized by the power-law decay of the autocorrelation function over several months.
Highlights
Information and Communication Technology enables large amounts of data related to human behaviors to be collected in milliseconds opening a novel research area of data-driven social sciences [1,2,3]
(7-day) periodicities are observed for each of the six emotional dynamics Zk(t). This is clearly indicated by the autocorrelation functions of each emotional dynamics ρk(τ) before excluding the periodic cycles which show weekly periodic correlations and sharp peak in the power spectrum densities Sk(f)
Extracting and tracing collective emotion is a challenging new research topic because social media has only become widespread in the past decade
Summary
Information and Communication Technology enables large amounts of data related to human behaviors to be collected in milliseconds opening a novel research area of data-driven social sciences [1,2,3]. Personal opinions and feelings that cannot be known directly from other sources are archived from blogs. More and more people are writing articles and share content on the Internet, for archival purposes, and for sharing them in real-time. Since the Internet population has already exceeded three billion and many people post their own texts online, various studies of Webbased phenomena have been conducted since the beginning of the twenty-first century. Diffusion phenomena on microblogging platforms such as Twitter have been well studied in various languages [4,5,6]. Studies on predicting real-world phenomena through the Internet data are rapidly growing, e.g., stock prices [9, 10], movie box office
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
