Bot comments Report February 2024

The dataset of toxic bot comments detected in February 2024 contained over 900 English messages (n=922) posted between February 1 and February 29. The average toxicity score was relatively low at 0.20. However, a noticeable spike in toxicity occurred on February 20, possibly linked to an event on that day: during the civil war in Myanmar, the liberation army claimed that shelling by the national army killed seven refugees (see the full list of events here).

Despite the low overall toxicity score, several messages featured highly problematic content with toxic keywords, including nazi, morons, Ioxist, fucking, rot in hell, kalergi plan, freaks, kill each other, Mexican, and nasty. The term "Kalergi plan" references a far-right antisemitic white genocide conspiracy theory, while "Ioxist" relates to Ioxism, a conspiracy theory claiming that Jews harbor hatred toward non-Jewish white people.

Toxicity was often associated with the categories Contempt (15%), Racism, Religion, and/or Politics. Additionally, 5% of the messages were classified under Threatening, and 2% contained Disinformation (see category definitions here).

The word cloud below displays the 50 most frequently used keywords from February 2024’s toxic bot comments. The size of each word reflects its relative frequency compared to others, with terms like jews, racist, feminism, and trump being among the most common.

This is the top 50 keywords used in February 2024 (threat = bold)

The table below highlights the various toxic categories detected in the February 2024 dataset, along with their respective frequencies (indicated by black dots and explained further below). Unlike previous months, no single category was significantly more prominent than the others. However, content focusing on Jews had the highest average toxicity score of 0.35 (on a scale from 0 to 1, where 1 indicates maximum toxicity).

Here are the keywords used per category in February 2024 

The bar chart below reveals that the category with the highest toxicity score in February 2024’s dataset of toxic bot comments was Profanity, followed by Politics, and then Ridicule, Contempt, and Religion (see the explanation of the different categories here). However, the majority of the content fell within the Politics category, indicating that the primary focus of the bot comments was on influencing political discussions.

The keyword network below visualizes the main focus of toxic bot comments in February 2024. Different colors represent clusters of words frequently used together, illustrating the key narratives pushed by the bot comments. A significant portion of the content appears to center around an antisemitic narrative, with keywords such as Israel, Ioxist, Jews, Zionist, and Ashkenazi forming strong connections. The term Ashkenazi refers to Jews of Central and Eastern European descent, often contrasted with Sephardic Jews, who originate from Mediterranean regions.

These were the keywords used by bots in January 2024 and the connections between these words