EFF Statement on Meta's Announcement of Revisions to Its Content Moderation Processes

In general, EFF supports moves that bring more freedom of expression and transparency to platforms—regardless of their political motivation. We’re encouraged by Meta’s recognition that automated flagging and responses to flagged content have caused all sorts of mistakes in moderation. Just this week, it was reported that some of those “mistakes” were heavily censoring LGBTQ+ content. We sincerely hope that the lightened restrictions announced by Meta will apply uniformly, and not just to hot-button U.S. political topics. 

Censorship, broadly, is not the answer to misinformation. We encourage social media companies to employ a variety of non-censorship tools to address problematic speech on their platforms and fact-checking can be one of those tools. Community notes, essentially crowd-sourced fact-checking, can be a very valuable tool for addressing misinformation and potentially give greater control to users. But fact-checking by professional organizations with ready access to subject-matter expertise can be another. This has proved especially true in international contexts where they have been instrumental in refuting, for example, genocide denial. 

So, even if Meta is changing how it uses and preferences fact-checking entities, we hope that Meta will continue to look to fact-checking entities as an available tool. Meta does not have to, and should not, choose one system to the exclusion of the other. 

Importantly, misinformation is only one of many content moderation challenges facing Meta and other social media companies. We hope Meta will also look closely at its content moderation practices with regards to other commonly censored topics such as LGBTQ speech, political dissidence, and sex work.  

Meta’s decision to move its content teams from California to “help reduce the concern that biased employees are overly censoring content” seems more political than practical. There is of course no population that is inherently free from bias and by moving to Texas, the “concern” will likely not be reduced, but just relocated from perceived “California bias” to perceived “Texas bias.” 

Content moderation at scale, whether human or automated, is impossible to do perfectly and nearly impossible to do well, involving millions of difficult decisions. On the one hand, Meta has been over-moderating some content for years, resulting in the suppression of valuable political speech. On the other hand, Meta’s previous rules have offered protection from certain types of hateful speech, harassment, and harmful disinformation that isn’t illegal in the United States. We applaud Meta’s efforts to try to fix its over-censorship problem but will watch closely to make sure it is a good-faith effort and rolled out fairly and not merely a political maneuver to accommodate the upcoming U.S. administration change.