Event Prediction in the Big Data Era

Abstract

Events are occurrences in specific locations, time, and semantics that nontrivially impact either our society or the nature, such as earthquakes, civil unrest, system failures, pandemics, and crimes. It is highly desirable to be able to anticipate the occurrence of such events in advance to reduce the potential social upheaval and damage caused. Event prediction, which has traditionally been prohibitively challenging, is now becoming a viable option in the big data era and is thus experiencing rapid growth, also thanks to advances in high performance computers and new Artificial Intelligence techniques. There is a large amount of existing work that focuses on addressing the challenges involved, including heterogeneous multi-faceted outputs, complex (e.g., spatial, temporal, and semantic) dependencies, and streaming data feeds. Due to the strong interdisciplinary nature of event prediction problems, most existing event prediction methods were initially designed to deal with specific application domains, though the techniques and evaluation procedures utilized are usually generalizable across different domains. However, it is imperative yet difficult to cross-reference the techniques across different domains, given the absence of a comprehensive literature survey for event prediction. This article aims to provide a systematic and comprehensive survey of the technologies, applications, and evaluations of event prediction in the big data era. First, systematic categorization and summary of existing techniques are presented, which facilitate domain experts’ searches for suitable techniques and help model developers consolidate their research at the frontiers. Then, comprehensive categorization and summary of major application domains are provided to introduce wider applications to model developers to help them expand the impacts of their research. Evaluation metrics and procedures are summarized and standardized to unify the understanding of model performance among stakeholders, model developers, and domain experts in various application domains. Finally, open problems and future directions are discussed. Additional resources related to event prediction are included in the paper website: http://cs.emory.edu/∼lzhao41/projects/event_prediction_site.html.

Involving machine learning techniques in heart disease diagnosis: a performance analysis

“…In this scenario, four mathematical equations are relied upon to find the effects of the techniques, which are: Accuracy: indicates the overall performance of the techniques (1), Sensitivity is the ratio of heart patients to the total number of patients in the dataset and it gives a positive confirmation of the patient's diagnosis (2), Specificity: is the diagnosis of healthy people as unhealthy (3), and Precision is the marker of a positive diagnosis made by the techniques (4). The last metric is the F1 score, which measures the probability that a positive diagnosis is correct (5).…”

“…In the past years, computers have been benefited from summarizing large amounts of data over time and making comments about events utilizing these data while performing calculations or transmitting data [3], [4]. Nowadays, computers can make decisions about events and know the relationship between events [5]. Also, computers can also solve issues that cannot be mathematically formulated.…”

Identifying geopolitical event precursors using attention-based LSTMs

“…In this section, we discuss research pertinent to our study. Over the last decade, there has been a significant interest in gaining insights into societal events, which are of two types: a) offline (e.g., protest, organized crime, and epidemic) and b) online (e.g., activism, petitions, and rumor) (Deng and Ning, 2021;Zhao, 2021). The modeling of such societal events falls under two broad categories-a) retrospective studies such as event detection (Yang et al, 1998) and summarization (Chakrabarti and Punera, 2011) and b) event forecasting (Zhao et al, 2018), i.e., anticipating future events.…”

Event prediction from news text using subgraph embedding and graph sequence mining

“…There exists various applications of event prediction across different domains. The works on this field can be categorized into temporal, spatial, semantic and joint prediction [ 47 ].…”

“…Event prediction is a comparatively more recent problem which focuses on predicting the features of the event, such as time, place, for a future time window. Many of the studies focus on event prediction for specific domains, such as social unrest, flood events, or business failures [ 47 ].…”