Prediction of COVID-19 Related Information Spreading on Twitter

Babić, Karlo; Petrović, Milan; Beliga, Slobodan; Martinčić-Ipšić, Sanda; Pranjić, Marko; Meštrović, Ana

doi:10.23919/mipro52101.2021.9596693

Cited by 9 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research is an extension of our previous studies of online communication on social media during the COVID-19 pandemic. In [63] we compared the retweeting of COVID-19 related tweets and tweets that are not related to COVID-19. Our findings indicate that tweets that almost 60% of tweets related to COVID-19 belong to the high-spreadable class; while less than 40% of non COVID tweets belong to this high spreadable class.…”

Section: Discussionmentioning

confidence: 99%

Retweet Prediction based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

Meštrović¹,

Petrović²,

Beliga³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Retweet prediction is an important task related to different problems such as information spreading analysis, the automatic detection of fake news, social media monitoring, etc. In this study we explore the possibilities of retweet prediction based on heterogeneous data sources. In order to classify the tweet according to the amount of retweets, we combine features extracted from the multilayer network and the text. More specifically, we introduce a multilayer framework that proposes the multilayer network representation of Twitter. This formalism captures different users' actions and complex relationships as well as other key properties of communication on Twitter. We select a set of local network measures from each layer and construct a set of multilayer network features. In addition, we adopt a BERT-based language model, namely Cro-CoV-cseBERT to capture high-level semantics and structure of tweets as a set of text features. Then, we train six machine learning (ML) algorithms: random forest, multilayer perceptron, light gradient boosting machine, category embedding model, neural oblivious decision ensembles and attentive interpretable tabular learning model in the task of retweet prediction. We compare the performance of all six algorithms in three different setups (i) using only text features, (ii) using only multilayer network features and (iii) using both sets of features. We evaluate all setups in terms of standard evaluation measures i.e. precision, recall, F1-score and accuracy. For this task, we first prepare and use an empirical dataset of 199,431 tweets in the Croatian language posted during the period between January 1, 2020 and May 31, 2021. Our results indicate that by integrating multilayer network features with text features the prediction model would perform better than using just one set of features.

show abstract

Section: Discussionmentioning

confidence: 99%

Retweet Prediction based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

Meštrović¹,

Petrović²,

Beliga³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This research is an extension of our previous studies of online communication on social media during the COVID-19 pandemic. In [72], we compared the retweeting of COVID-19-related tweets and tweets that are not related to COVID-19. Our findings indicate that nearly 60% of tweets related to COVID-19 belong to the high-spreadable class, whereas less than 40% of non-COVID-19 tweets belong to this high-spreadable class.…”

Section: Discussion On Retweet Prediction Based On Heterogeneous Feat...mentioning

confidence: 99%

Retweet Prediction Based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

2022

Self Cite

View full text Add to dashboard Cite

Retweet prediction is an important task in the context of various problems, such as information spreading analysis, automatic fake news detection, social media monitoring, etc. In this study, we explore retweet prediction based on heterogeneous data sources. In order to classify a tweet according to the number of retweets, we combine features extracted from the multilayer network and text. More specifically, we introduce a multilayer framework for the multilayer network representation of Twitter. This formalism captures different users’ actions and complex relationships, as well as other key properties of communication on Twitter. Next, we select a set of local network measures from each layer and construct a set of multilayer network features. We also adopt a BERT-based language model, namely Cro-CoV-cseBERT, to capture the high-level semantics and structure of tweets as a set of text features. We then trained six machine learning (ML) algorithms: random forest, multilayer perceptron, light gradient boosting machine, category-embedding model, neural oblivious decision ensembles, and an attentive interpretable tabular learning model for the retweet-prediction task. We compared the performance of all six algorithms in three different setups: with text features only, with multilayer network features only, and with both feature sets. We evaluated all the setups in terms of standard evaluation measures. For this task, we first prepared an empirical dataset of 199,431 tweets in Croatian posted between 1 January 2020 and 31 May 2021. Our results indicate that the prediction model performs better by integrating multilayer network features with text features than by using only one set of features.

show abstract

“…In our previous work, we analyzed isolated online and social media content published in the Croatian language in a shorter time period [35][36][37][38]. In this study, we focused on the eight major representatives of online news media by scrutinizing their publications over a significantly longer period (from January 1, 2020, to January 15, 2021).…”

Section: Descriptive Analysis Of the Online Newspaper Spacementioning

confidence: 99%

Infoveillance of the Croatian Online Media During the COVID-19 Pandemic: One-Year Longitudinal Study Using Natural Language Processing (Preprint)

Beliga¹,

Martinčić-Ipšić²,

Matešić³

et al. 2021

Preprint

View full text Add to dashboard Cite

BACKGROUND Online media plays an important role in public health emergencies and serves as a communication platform. Infoveillance of online media during the COVID-19 pandemic is an important step toward a better understanding of crisis communication. OBJECTIVE The goal of this study is to perform a longitudinal analysis of the COVID-19 related content based on natural language processing methods. METHODS We collected dataset of news articles published by Croatian online media during the first 13 months of the pandemic. Firstly, we test the correlations between the number of articles and the number of new daily COVID-19 cases. Secondly, we analyze the content by extracting the most frequent terms and apply the Jaccard similarity. Next, we compare the occurrence of the pandemic-related terms during the two waves of the pandemic. Finally, we apply named entity recognition to extract the most frequent entities and track the dynamics of changes during the observed period. RESULTS The results show there is no significant correlation between the number of articles and the number of new daily COVID-19 cases. Furthermore, there are high overlaps in the terminology used in all articles published during the pandemic with a slight shift in the pandemic-related terms between the first and the second wave. Finally, the findings indicate that the most influential entities have lower overlaps for identified persons and higher overlaps for locations and institutions. CONCLUSIONS Our study shows that online media has a prompt response to the pandemic with a large number of COVID-19 related articles. There is a high overlap in the frequently used terms across the first 13 months, which may indicate the lower quality of reporting in certain periods. However, the pandemic-related terminology is well covered.

show abstract

Prediction of COVID-19 Related Information Spreading on Twitter

Cited by 9 publications

References 21 publications

Retweet Prediction based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

Retweet Prediction based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

Retweet Prediction Based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

Infoveillance of the Croatian Online Media During the COVID-19 Pandemic: One-Year Longitudinal Study Using Natural Language Processing (Preprint)

Contact Info

Product

Resources

About