Bot comments Report April 2024

The dataset of toxic bot comments detected in April 2024, spanning from April 1 to April 30, included over 2,240 English messages (n=2,249). The average toxicity score was relatively low at 0.20, though a significant peak was observed on April 17, 2024. Possible events contributing to this spike include the Russian invasion of Ukraine, the Iran-Israel conflict, or the Israel-Hezbollah conflict (see the full list of events here).

Despite the low average toxicity score, some messages contained highly problematic content featuring toxic keywords such as idiot, moron, filthy Jew, tards, libtards, zionazis, bitch, fat, and Christian.

  • 4 messages were classified as very toxic, with scores exceeding 0.8.

  • 15% of the messages involved categories such as Ridicule, Politics, Profanity, and/or Religion.

  • About 10% contained Threatening content, and 2% included Disinformation.

  • The most frequent combination was Politics + Religion (see category explanations here).

The word cloud below highlights the 50 most frequently used keywords in the dataset from April 2024. The size of each word reflects its relative frequency, with genocide being used the most by far, followed by terrorist, killed, black, Israel, and Trump.

These words form the top 50 keywords used in April 2024 by bot comments (THREAT = bold)

The table below highlights the various toxic categories detected within the dataset for April 2024, along with their respective frequencies (represented by black dots and further explained below). The most prominent categories were Politics, Religion, and Threats. However, the category Jews had the highest average toxicity score of 0.40 (on a scale of 0 to 1, where 1 represents the highest level of toxicity).

The bar chart below reveals that the most prominent category with the highest toxicity score in April 2024’s dataset of toxic bot comments was Ridicule, followed by Politics. However, the majority of the bot content fell under the Politics category, indicating that the primary aim of the toxic bot comments was to influence political discussions. Additionally, the categories Politics and Threats contained the highest proportion of content with a toxicity score exceeding 0.8 (see the explanation of the different categories here).

Number of toxic messages by category in April 2024

The keyword network below visualizes the primary focus of toxic bot comments within the April 2024 dataset. Different colors represent clusters of frequently co-occurring words, revealing the dominant narratives promoted by bot content. One of the most prominent narratives revolves around the Israel-Gaza conflict, with key terms such as Israel, Palestinian, die, land, terrorist, and genocide forming strong associations. This cluster highlights how bot content centered on themes of conflict, violence, and territorial disputes.

Previous
Previous

Call for Proposals from NGOs to get Subcontracted for the 8th Monitoring Exercise to Monitor the Code of Conduct on Tackling Online Hate Speech

Next
Next

Tracing Online Misogyny