The proliferation of yellow journalism or fake news and the way it is spreading, especially on social media, has become a big concern because of its devastating effects. While the information we require is just a click away, there is also a lot of misinformation on products, religion, communities, etc., on the internet that spreads further via social media, print and news channels.

There’s almost no restriction by social media platforms on the content that gets published. Most of the people do not verify the source of the information that they browse online before they share it, thus leading to fake news spreading rapidly or even going viral.

Moreover, it’s very difficult to identify the source of such information, thus making it harder to assess their accuracy. . Social media has become a dominant source of news and information and has dramatically reshaped the media industry.

However, fake news existed long before the arrival of social media. It became a buzzword after the US presidential elections in 2016. The internet has given a boost to fake news, be it fallacious reporting or rumour-mongering.

The good news is that in the near future artificial intelligence or, to be more specific, machine learning-based models will help a user to check whether the news is real or fake. Even though research in this area is going on, there’s still a lot more to be done. A particular area of research known as natural language processing (NLP) is receiving a lot of attention from scholars and academicians across the globe.

Automated detection

With the number of users of online media growing, automated detection seems to be the only way to tackle fake news. So far there have been text-based approaches to detect fake news, but these have not yielded the desired results. Almost all the machine-learning models use hand-crafted features extracted from input textual content.

In the future, we will witness a context-based approach in detecting fake news. In 2016, some researchers found that almost half of the news on Facebook is fake and hyper-partisan. And news agencies depend on Facebook for 20 per cent of their traffic.

Fake news has been spreading through Twitter also. Recently. thanks to a new approach, it was found that fake news was being tweeted during the Covid-19 pandemic to mislead the targeted population. Machine learning and highly sophisticated deep learning models are being continuously used by researchers and industrialists to develop automated fake news detection-based models.

Many such models detect particular types of news such as political and on religion. Some research journals reveal that such models have features for specific datasets that match their topic of interest. Such approaches might suffer from dataset bias and perform poorly on news of another topic.

Much more advanced

Deep learning-based models are bringing a revolution in almost every walk of life. The recent developments in natural language processing, hold promise in detecting fake news. With the advent of Keras (an API in deep learning) and Tensorflow (end-to-end open-source platform for machine learning), coding and implementation of such intelligent models have become a lot easier compared to a decade back.

In the future, deep learning models will be able to classify fake news and legitimate news. Decades of experiments in deception detection show that humans are not good at identifying lies in text.

The spread of fake news hurts the behaviour, beliefs, and attitudes of the public which, in turn, can endanger the democratic processes. Early detection of such false information and checking their spread are the main challenge for researchers today.

The writer is Associate Professor, Great Lakes Institute of Management, Gurgaon

comment COMMENT NOW