Zoekresultaten

Fringe players on political Twitter

So-called fake news and problematic information on social media assume an increasingly important roles in political debate. Focusing on the (early) run-up to and aftermath of the 2020 U.S. presidential elections, this study examines the extent of the problematic information in the most engaged-with content and most active users in ‘political Twitter’. We demarcated three time spans, the first surrounding Super Tuesday (March 2-22, 2020), the second providing a snapshot of the aftermath of the elections and the run-up to both the Senate run-off elections in Georgia (December 24, 2020 – January 4, 2021) and the (unforeseen) Capitol Hill riots on January 6, 2021. In the third time span (March 10-21, 2021), when election activities had ceased, we examine the effects of Twitter’s deplatforming (or so-called purge) of accounts after the Capitol riots in January, 2021. In order to shed light on the magnitude of problematic information, we mapped shared sources, labelled them and assessed the actors engaged in their dissemination. It was found that overall, mainstream sources are shared more often than problematic ones, but the percentage of problematic sources was much higher in December compared to both the March, 2020 and 2021 periods. Significantly, (hyper)partisan sources are close to half of all sources shared in the first two periods, implying a robust presence of them on social media. By March 2021, both the share of problematic and of (hyper)partisan sources had decreased significantly, suggesting an impact from Twitter’s deplatforming actions. Additionally, highly active, problematic users (fake profiles, bots, or locked/suspended accounts) were found on both sides of the political spectrum, albeit more abundantly from conservative users.

The added value of advisory services in SME mergers and acquisitions

The objective of this study is to shed light on the added value of the services of five disciplines in M&A advisory in the SME domain: accountants, bankers, business brokers, fiscalists and lawyers. Theory is inconclusive in the added value of advisory services and research on the subject is hardly available. RBV predicts direct benefits in using advisory services in M&A, leading to less obstacles in and directly after M&A or lagged effects on more renewal of the firm. The theory of structural holes, agency theory and management entrenchment theory on the other hand predict neutral or negative effect of advisory services in M&A. The dataset includes 899 mergers and acquisitions (1) completed before 2003; (2) with an acquirer having bought 100% of target shares or assets; (3) of German, Belgian or Dutch origin; (4) of non-listed firms; (5) where acquirer and target firm are not member of the same family. Using (M)ANOVA’s and controlling for the effects of more than one advisor involved, the outcomes show consistently that the M&A advisory services do not reduce obstacles like financing, misinformation and culture and staff problems during or immediately after M&A. Looking at lagged effects of advisory services in the period of two years after M&A strategic more renewal by innovation occurs if bankers, fiscalists and lawyers are involved. Involvement of accountants and business brokers on the other hand decrease renewal.

The earnest platform

Increasingly, Instagram is discussed as a site for misinformation, inau-thentic activities, and polarization, particularly in recent studies aboutelections, the COVID-19 pandemic and vaccines. In this study, we havefound a different platform. By looking at the content that receives themost interactions over two time periods (in 2020) related to three U.S.presidential candidates and the issues of COVID-19, healthcare, 5G andgun control, we characterize Instagram as a site of earnest (as opposedto ambivalent) political campaigning and moral support, with a rela-tive absence of polarizing content (particularly from influencers) andlittle to no misinformation and artificial amplification practices. Mostimportantly, while misinformation and polarization might be spreadingon the platform, they do not receive much user interaction.

Explainable misinformation detection from text

Explainable Misinformation Detection from Text: A Critical Look

With the proliferation of misinformation on the web, automatic methods for detecting misinformation are becoming an increasingly important subject of study. If automatic misinformation detection is applied in a real-world setting, it is necessary to validate the methods being used. Large language models (LLMs) have produced the best results among text-based methods. However, fine-tuning such a model requires a significant amount of training data, which has led to the automatic creation of large-scale misinformation detection datasets. In this paper, we explore the biases present in one such dataset for misinformation detection in English, NELA-GT-2019. We find that models are at least partly learning the stylistic and other features of different news sources rather than the features of unreliable news. Furthermore, we use SHAP to interpret the outputs of a fine-tuned LLM and validate the explanation method using our inherently interpretable baseline. We critically analyze the suitability of SHAP for text applications by comparing the outputs of SHAP to the most important features from our logistic regression models.

Exploring Bias in Data and Models for Misinformation Detection from Text

With the proliferation of misinformation on the web, automatic misinformation detection methods are becoming an increasingly important subject of study. Large language models have produced the best results among content-based methods, which rely on the text of the article rather than the metadata or network features. However, finetuning such a model requires significant training data, which has led to the automatic creation of large-scale misinformation detection datasets. In these datasets, articles are not labelled directly. Rather, each news site is labelled for reliability by an established fact-checking organisation and every article is subsequently assigned the corresponding label based on the reliability score of the news source in question. A recent paper has explored the biases present in one such dataset, NELA-GT-2018, and shown that the models are at least partly learning the stylistic and other features of different news sources rather than the features of unreliable news. We confirm a part of their findings. Apart from studying the characteristics and potential biases of the datasets, we also find it important to examine in what way the model architecture influences the results. We therefore explore which text features or combinations of features are learned by models based on contextual word embeddings as opposed to basic bag-of-words models. To elucidate this, we perform extensive error analysis aided by the SHAP post-hoc explanation technique on a debiased portion of the dataset. We validate the explanation technique on our inherently interpretable baseline model.