Thursday, May 23, 2024
machine learning identified taboos


A taboo is commonly defined as an action that is prohibited or restricted by social or religious customs. Moreover, a taboo is a topic that is often hard to discuss, other times unmentionable, and cases where it can even be considered unthinkable. Taboos are cultural productions, embedded socially and historically, that vary from one society to another, although some taboos can be regarded as universal.

The established social norms and taboos largely govern the behavior and lives of a culture or society. Nevertheless, behaviors, societies, and in effect, taboos do not remain constant over time. Taboos are created and destructed through various processes in societies. Many might feel that currently, there are almost no taboos left, at least in Western societies, since the breaking of a taboo represents an example of social progress. However, many examples of taboos existing today can still be found.

Artists commonly attempt to bend the boundaries, challenge, and confront conventions and taboos. Yet, we can still find very recent examples of artworks that have been banned, removed from exhibitions, and threatened with lawsuits. Such works dealt with religious beliefs, nudity, political correctness, sexual content, and many other topics that are contemporary taboos in many societies. Despite that, artworks have always contributed to making something previously unacceptable become acceptable through critical acclaim or sheer exposure.

Prohibition, shame, and guilt lead to silence that is used in societies to maintain taboos. But how can one study taboos, their creation, maintenance, and destruction, if absolute silence is imposed on them? Exploring taboos is only possible when this silence is broken. The breaking of silence is observable and socially more significant as it indicates an ongoing related social process for creating, maintaining, or destructing a taboo. The work presented in this paper adopts the importance of the breaking of silence on taboo topics, and thus its title Breaking the Silence.

Breaking the Silence uses machine learning methods to understand what are the contemporary taboo topics. 

Initially, news articles that contained the word taboo were mined from various online sources. The mined articles were originally posted from January 2019 to September 2020. These articles include overt references to contemporary taboo topics in today’s press as well as the report of transgressions. Natural Language Processing (NLP) methods are then used to identify the main topic of each mined article and thus group them into sets according to similarity and relevance. Next, techniques for information extraction are used to determine the most meaningful elements of the articles’ text like entities, abstract concepts, etc. Finally, new documents are generated with the utilization of automatic text summarization techniques. These generated documents summarize the main ideas and opinions for each identified taboo topic. The images shown in all articles were generated with Runaway Generative Engine by randomly selecting sentences from each article.

Breaking the Silence aims to highlight and bring to focus what topics are currently discussed as taboos. The generated summarizations underline the different topics discussed at different times and additionally the arguments for the creation, maintenance, or destruction of a taboo.

Breaking The Silence was created by Amalia Foka.