A new insight into combining forecasts for elections: The role of social media

Abstract

This study is devoted to gain insight into a timely, accurate, and relevant combining forecast by considering social media (Facebook), opinion polls, and prediction markets. We transformed each type of raw data into the possibility of victory as a forecasting model. Besides the four single forecasts, namely Facebook fans, Facebook "people talking about this" (PTAT) statistics, opinion polls, and prediction markets, we generated three combined forecasts by associating various combinations of the four components. Then, we examined the predictive performance of each forecast on vote shares and the elected/nonelected outcome across the election period. Our findings, based on the evidence of Taiwan's 2018 county and city elections, showed that incorporating the Facebook PTAT statistic with polls and prediction markets generates the most powerful forecast. Moreover, we recognized the matter of the time horizons where the best proposed model has better accuracy gains in predictionin the "late of election," but not in "approaching election". The patterns of the trend of accuracy across time for each forecasting model also differ from one another. We also highlighted the complementarity of various types of data in the paper because each forecast makes important contributions to forecasting elections.

Assessing the Accuracy of Google Trends for Predicting Presidential Elections: The Case of Chile, 2006–2021

“…This finding is consistent with Schoen et al who indicate that the best mechanism for predicting futures from social networks is through advanced statistical methods [14] [17]. Chin and Wang apply predictive time series techniques to review the predictive value of social networks against the 2018 Taiwan election, indicating that incorporating Facebook into the analysis matrices used considerably increases the predictive value [18]. Unlike the aforementioned cases, this article contributes using a statistical method little explored for these cases, namely the prediction model using an ARIMA model from serial data collected in Google Trends for different social networks.…”

Asessing the Accuracy of Google Trends for Predicting Presidential Elections: The Case of Chile 2006-2021

“…Chin and Wang apply predictive time series techniques to review the predictive value of social networks against the 2018 Taiwan election, indicating that incorporating Facebook into the analysis matrices used considerably increases the predictive value. (Chin & Wang, 2021). Unlike the aforementioned cases, this article contributes using a statistical method little explored for these cases, which is the prediction model using an ARIMA model from serial data collected in Google Trends for different social networks.…”