Guest Editorial: Big Social Data Analysis

In the era of social connectedness, Web users are becoming increasingly enthusiastic about interacting, sharing, and collaborating through online collaborative media. In recent years, this collective intelligence has spread to many different areas, with particular focus on fields related to everyday life such as commerce , tourism, education, and health, causing the size of the social Web to expand exponentially. The distillation of knowledge from such a large amount of unstructured information, however, is an extremely difficult task, as the contents of today's Web are perfectly suitable for human consumption, but remain hardly accessible to machines. Big social data analysis grows out of this need and combines disciplines such as social network analysis, multimedia management , social media analytics, trend discovery, and opinion mining. For example, studying the evolution of a social network merely as a graph is very limiting as it does not take into account the information flowing between network nodes. Similarly, processing social interaction contents between network members without taking into account connections between these is limited by the fact that information flows cannot be properly weighted. Big social data analysis, instead, aims to study large-scale Web phenomena such as social networks from a holistic point of view, i.e., by concurrently taking into account all the socio-technical aspects involved in their dynamic evolution. Hence, big social data analysis is inherently interdisciplinary and spans areas such as machine learning, graph mining, information retrieval, knowledge-based systems, linguistics, common-sense reasoning, natural language processing, and big data computing. Accordingly, the contained articles in this issue cover variegated topics including stock market prediction, political forecasting, time-evolving opinion mining, social network analysis, and human–robot interaction. Out of the forty submissions received for this special issue, twelve were accepted. Three of the accepted papers underwent four rounds of revisions, four papers underwent three, and the rest underwent two revisions. The article ''Time Corpora: Epochs, Opinions and Changes'' by Octavian Popescu and Carlo Strapparava proposes to explore dia-chronic phenomena by using large corpora of chronologically ordered language and, hence, identify previously unknown correlations between language usage and time periods, or epochs. Authors focus on a statistical approach to epoch delimitation and introduce the task of epoch characterization. They investigate the significant changes in the distribution of terms in the Google N-gram corpus and their relationships with emotion words. Deng first implement a generic stock price prediction framework and plug in six different models with different …