Correlations and fluctuations in the word sets of collective emotions

Abstract

Abstract:In recent times, research on extracting collective emotion from social media has been actively pursued. When constructing collective emotions from social media, a bag-ofwords, which is made of an aggregation of related words' frequencies, is often used. However, correlations between targeted words, as well as fluctuations under the word aggregation process, have attracted little attention. In this research, we examine the correlations and fluctuations of words contained within the collective emotion in Japanese blogs. From our result, we found that correlations between words belonging to the same emotion tend to be higher than correlations between different emotions, and the fluctuation is reduced by the aggregation process. We believe that our conclusion is applicable not only to the frequency of occurrence of words but also to systems consisting of small components in various contexts.

Identifying long-term periodic cycles and memories of collective emotion in online social media

“…We first generate the time series for word i that belongs to emotion k at day t , , and define the time series of emotion k as follows: where M k is the number of words that belong to emotion k . Because the appearance of a word in the emotion dictionary can easily fluctuate due to news and external factors, summing up several words can reduce the fluctuation [ 28 ].…”

“…where M k is the number of words that belong to emotion k. Because the appearance of a word in the emotion dictionary can easily fluctuate due to news and external factors, summing up several words can reduce the fluctuation [28]. Next, to determine each of the emotional dynamics, we calculate each emotion's time series Z k (t).…”

“…In principle, the database can be used by anyone if contracted with the company (https://www.hottolink.co.jp/: Accessed August 24, 2018)'. In fact, various studies have been conducted based on the database so far [27][28][29]. Due to the system specification, if one blog article contained the same word multiple times, we counted it once.…”