Inferring the votes in a new political landscape: the case of the 2019 Spanish Presidential elections

Abstract

For more than a decade now, with the emergence of Internet 2.0, users have been able to generate their own content and share it publicly with relative ease. This boom has witnessed a huge surge in the popularity of Online Social Networks (OSN), in particular the Twitter microblogging platform which allows its users to share text messages of up to 140 characters with their family, friends and followers [12]. More than 500 million messages, commonly known as tweets, are posted every day [20, 34]. Given that the main reason behind these publications is to express the opinion of the users, they have proven to be great interest to be analysed [14, 38, 48]. This huge amount of content circulating in OSN has attracted the attention of marketing agencies that seek capitalize on the behaviour of clients (current or future) to adjust their online campaigns and even use the social content (number of likes, retweets, etc.) to predict consumer behaviour in the real world [45, 53]. Recently this type of analysis

Public opinion monitoring through collective semantic analysis of tweets

“…Advancing on this line of research, Grimaldi et al. ( 2020 ) aimed to predict not only the winner but also the voting share of each candidate in the 2019 Spanish Presidential elections, by considering the volume of positive tweets per candidate. Still, the semantic attributes themselves were not aggregated over the set of all tweets.…”

“…Grimaldi et al. ( 2020 ) evaluates a variety of traditional (non-neural) machine learning algorithms, while (Kraaijeveld and De Smedt 2020 ) exploits a sentiment analysis rule set (Hutto and Gilbert 2014 ). Recent DNN-based learning models were only exploited in El Barachi et al.…”

Forecasting elections results via the voter model with stubborn nodes

“…A pioneer work in this area was that of Tumasjan et al (2011) whose model achieved a mean average error (MAE) of 1.65% when predicting results of the 2009 German federal election. Authors used Twitter mention counts as an direct indicator of a candidate's popularity, a method that has been considered by several other works as well, often in combination with a sentiment analysis of tweets content (O'Connor et al 2010;Saleiro et al 2016;Garcia et al 2018;Grimaldi et al 2020;Fink et al 2013;Huberty 2013;Caldarelli et al 2014;Thapen and Ghanem 2013). In particular, Garcia et al (2018) achieved 90% accuracy in predicting the top two candidates in various municipalities during Brazilian municipal elections, and Saleiro et al (2016) achieved a MAE of 0.63% when trying to predict opinion poll results during the Portuguese bailout (2011-2014).…”

Dynamic Restaurants Quality Mapping Using Online User Reviews

“…They claim OGRs could fill this gap, even if the idiosyncratic nature of data collection brings specific challenges [10,11]. Understanding of this information, therefore, remains rather poor, despite the importance of OGRs in decision-making about buying a product [12], listening to music [13], voting for a presidential election [14][15][16][17][18], or choosing a restaurant [19][20][21]. Consequently, the present study extends incipient research into the question of how to put OGRs to good use for restaurant inspection purposes, protecting citizens' health in the process.…”