A Tool for Hate Speech Detection on the Internet is Being Developed
As the number of online hate comments increases, artificial intelligence comes to the aid: researchers from Vytautas Magnus University (VMU), together with the Lithuanian Human Rights Center, European Foundation of Human Rights and the Department of National Minorities under the Government of the Republic of Lithuania are developing a tool that will help to automatically detect and remove cases of hate speech, for instance, in the comment sections of news portals. According to one of the project developers, Professor Tomas Krilavičius, Dean of the VMU Faculty of Informatics, the development of such a tool is quite challenging: people themselves often find it difficult to recognize hate speech, and artificial intelligence needs to be thoroughly trained to do so.
“While working with social networking texts and comments at the university, we noticed a lot of negative things, incitement to hatred. However, recognizing hate speech is difficult for artificial intelligence: good and effective solutions in this area have not yet been proposed for any language since the definition of hate speech itself requires careful consideration of the context. Moreover, there is no clear legal regulation, and people themselves sometimes disagree on what counts as hate speech and what does not,” says the professor.
He also notes that hate speech is not a comment or insult directed against a specific person, but rather an attack on weaker groups of society, such as national minorities or LGBT communities, and threats against them. “In other words, if you write something mean only about me, it’s not going to count as hate speech. But if certain vulnerable groups are attacked and threatened with violence, then it will count as hate speech,” the researcher explains. According to Krilavičius, the tool for hate speech detection will use artificial intelligence and language technology to assess the likelihood that a particular text is hate speech.
Prof. Tomas Krilavičius (Photo by Jonas Petronis)
This solution could be particularly useful for news portals that wish to keep their comment sections clean. Researchers are currently improving the tool by using sample texts that the artificial intelligence will later make use of when assessing other cases. The focus is on short texts, such as messages, comments, and posts on social networks. During the project, experts in artificial intelligence, technology, linguistics, law and other fields are collaborating to develop the tool.
“We use many examples, some of which are marked as hate speech, and some of which are not. Such artificial intelligence solutions learn from various examples and word combinations. Using more sophisticated methods, it is possible to detect that some word may be used instead of another similar word in a similar context. We have already reviewed many methods and experimented with a small data set, and now we will try a larger one,” says Professor Krilavičius.
While the tool is expected to be very useful in combating hate speech on the Internet, professor maintains that artificial intelligence in such solutions only assists people and will not replace them for a long time to come, as understanding context and having additional knowledge such as the ability to recognize sarcasm is crucial. Thus, in some cases, it will be necessary for a person to assess possible manifestations of hate speech.
“The tool will indicate in percentage terms the probability that the text analyzed is hate speech. For example, if the probability reaches 70 percent, the comment will be automatically blocked, and if it reaches only 50 percent, it will be published. However, if the probability is between 50 and 70 percent, then the comment will be temporarily blocked and handed over to people for verification,” VMU professor describes the principle of the functioning of the tool.
The main challenges in developing the tool include not only the fact that there is a lot of debate about the definition of hate speech, but also the fact that there is an insufficient number of examples from which artificial intelligence can learn. “We don’t have enough corpora and marked examples, and preparing them takes a lot of work. Furthermore, the training of those models of artificial intelligence requires a considerable amount of computational resources,” says Professor Krilavičius.
The tool was developed also based on foreign research and solutions, mainly in English. However, as can be seen from the comments on Facebook and other platforms, there are currently no solutions that could effectively identify and remove hate speech. The tool under development is expected to contribute to progress in this area.
Professor Krilavičius will discuss more about hate speech at the National Forum on Human Rights, which will take place on December 10 at the Martynas Mažvydas National Library of Lithuania. During the discussion “Hate speech: the individual and the community”, together with other participants of the event, he will discuss relevant issues, such as where is the line between hate speech and freedom of speech, how technology helps to combat hate speech, etc. The discussion is part of the project “Be Hate-Free: Building Hate-Free Communities in Lithuania.”
It is expected that the tool for hate speech detection developed by Vytautas Magnus University together with the Lithuanian Human Rights Center, European Foundation of Human Rights and the Department of National Minorities under the Government of the Republic of Lithuania will be ready for use in spring 2022. In addition to developing the tool, researchers working on the project will also develop guidelines on how to use it and organize training and discussions to help identify hate speech and understand its causes and origins.
