Filtering the intensity of public concern from social media count data with jumps

  title={Filtering the intensity of public concern from social media count data with jumps},
  author={Matteo Iacopini and Carlo Romano Marcello Alessandro Santagiustina},
  journal={Journal of the Royal Statistical Society: Series A (Statistics in Society)},
Count time series obtained from online social media data, such as Twitter, have drawn increasing interest among academics and market analysts over the past decade. Transforming Web activity records into counts yields time series with peculiar features, including the coexistence of smooth paths and sudden jumps, as well as cross‐sectional and temporal dependence. Using Twitter posts about country risks for the United Kingdom and the United States, this paper proposes an innovative state space… 

Impact of Public News Sentiment on Stock Market Index Return and Volatility

This paper investigates the impact of the release of public financial news on the S&P 500 and finds that dictionary-based sentiment provides meaningful results with respect to those based on stock index returns, which partly fails in the mapping process between news and financial returns.

Enhancing (publications on) data quality: Deeper data minding and fuller data confession

This commentary argues that it would benefit statistics and (data) science if statisticians were also to treat data as products in and of themselves, and accordingly subject them to data minding, a stringent quality inspection process that scrutinizes data conceptualization, data pre‐processing, data curation and data provenance.



The Effects of Twitter Sentiment on Stock Price Returns

Investigating the relations between a well-known micro-blogging platform Twitter and financial markets shows that sentiment polarity of Twitter peaks implies the direction of cumulative abnormal returns.

Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump

A method to infer the opinion of Twitter users by using a combination of statistical physics of complex networks and machine learning based on hashtags co-occurrence to build an in-domain training set of the order of a million tweets is developed.

The social amplification of risk on Twitter: the case of ash dieback disease in the United Kingdom

It has long been recognised that the traditional media play a key role in representing risk and are a significant source of information which can shape how people perceive and respond to hazard

Debanalizing Twitter: the transformation of an object of study

This paper enquires into how Twitter has been studied since it was launched in 2006 as an ambient friend-following and messaging utility, modelled after dispatch communications, and provides a framework to situate past, current and future Twitter research.

A Bayesian Approach for Predicting the Popularity of Tweets

A probabilistic model for the evolution of the retweets is developed using a Bayesian approach, and predictions are formed using only observations on the retweet times and the local network or "graph" structure of the retweeters.

Social Amplification of Risk in the Internet Environment

  • I. Chung
  • Sociology
    Risk analysis : an official publication of the Society for Risk Analysis
  • 2011
The dynamic process of risk amplification in the Internet environment with special emphasis on public concern for environmental risks from a high-speed railway tunnel construction project in South Korea is analyzed.

Modelling non‐stationary multivariate time series of counts via common factors

We develop a new parameter‐driven model for multivariate time series of counts. The time series is not necessarily stationary. We model the mean process as the product of modulating factors and

Spatial, temporal, and content analysis of Twitter for wildfire hazards

Social media data are increasingly being used for enhancing situational awareness and assisting disaster management. We analyzed the wildfire-related Twitter activities in terms of their attributes

Bayesian Forecasting of Many Count-Valued Time Series

  • L. BerryM. West
  • Computer Science
    Journal of Business & Economic Statistics
  • 2019
A novel multiscale approach—one new example of the concept of decouple/recouple in time series—enables information sharing across series, and hence enables scalability in the number of series.

Beyond Words: Amplification of Cancer Risk Communication on Social Media

Comparing the modality of risk-related messages, videos were not more effective in attracting audience engagement than images, suggesting that future studies should examine risk signal recognition and dissemination as separate behaviors.