Al Jazeera Journalism Review

Outside image
Artificial intelligence (AI) has many potential uses in the newsroom but its potential dangers are no less great. GPT Chat is one popular example of AI [Shutterstock]

AI in the newsroom - how it could work

AI is now our colleague in the newsroom and is poised to become even more helpful as it gets smarter and we see more opportunities - we look at all the potential uses and problems


There are already a few examples of how AI can be tuned to assist journalism. Almost all require a human hand to supervise, edit, refine and approve - which, currently, is a good thing.

This recent report by the World Association of News Publishers finds that “half of newsrooms already work with Generative AI tools”; that “content summaries are the most common use case” for AI in the newsroom; and lists some of the current uses of AI for journalism.

I am adding a few potential uses below. I guess that many of these ideas will soon find their way into the Content Management Systems we use daily. They will become an automated function; we will set parameters, “press a button”, and then AI will take over.


Read more:

What is ChatGPT and why is it important for journalists?

What happened when I asked ChatGPT to write my article



Of course, with ease of use come concerns, some obvious and some hard to see. If I made it sound like the famous Spiderman line, “With great power comes great responsibility”, I did it on purpose.


Real-time transcription

What is it: The use of GPT for transcribing audio and video recordings, interviews, live speeches, panel discussions and podcasts.

How it could be done: By connecting the GPT model to a source audio stream. It will process the recording and produce a text transcription of the spoken content. There needs to be some manual work to fix any inaccuracies that may have occurred due to speech recognition.

How it will help: It can help journalists focus on editorial work rather than spend time doing manual transcription. It can also help address accessibility issues by providing audiences with immediate and accurate transcriptions.

Potential problems: GPT may have problems accurately transcribing the nuances of different accents, languages or dialects.


Multilingual content

What is it: GPT can translate articles, news reports, scripts and subtitles into multiple languages.

How it could be done: Feed source articles to GPT and select a language it has been trained on. A journalist should manually post-process the translation to fix inaccuracies and make refinements.

How it will help: AI-powered multilingual content can greatly increase the reach and accessibility of news stories to wider audiences.

Potential problems: AI-generated translations may fail to recognise idiomatic expressions, ambiguous terms and regional dialects.


Text simplification

What is it: GPT models can simplify complex articles into more accessible language, catering to different reading levels.

How it could be done: By establishing guidelines before the process, essentially explaining to GPT the parameters for simplification, reading level, the editorial voice and house style.

How it will help: It will be easier for non-native speakers, people with reading difficulties or simply those with little time to spend on the news to access a brand’s journalism. It would also make news content discoverable by search engines and optimised for audience needs.

Potential problems: When a source text is simplified, there may be issues with accuracy, context and the possibility that AI could miss essential information. Also, potential problems in narrative, tone of voice and style.


Headline and summary generation

What is it: GPT models can generate multiple headlines for an article, allowing editors to select the most appropriate or engaging one to publish. They could also quickly draft a brief and concise summary of a lengthy article.

How it could be done: A GPT model would process an article and identify the key points, condensing them into a summary - this is a task that ChatGPT routinely does now. It can then put together relevant titles; the editor can ask it to format them to target specific audiences.

How it will help: Saving time in the newsroom and making journalism accessible to people who do not have much time to devote to news reading.

Potential problems: As with most automated features and editorial work, ensuring AI captures context correctly is essential. Also, there could be issues when summarising opinion pieces, where GPT could alter the writer's voice. 


Article drafting

What is it: GPT models can generate an initial draft based on given headlines or content briefs before a journalist edits and polishes it.

How it could be done: Some AI models are already compiling article drafts starting with a list of questions or Google SERP data (the questions listed below the search results as “People Also Ask” and are meant to expand the search parameters). In a newsroom, this could be a routine process that would create a starting point for editors to fact-check and verify before publishing.

How it will help: It could save time and allow journalists to focus on more complex tasks. Time and better training will certainly improve the quality of the first drafts. Also, GPT models, which “learn” as they go, will eventually better understand context and complexities.

Potential problems: The quality and trustworthiness of AI-generated text are not there yet. There are also all sorts of ethical implications, questions about biases and misinformation that may stem from a piece of journalism that a human journalist does not prepare. And then there’s the news brand's editorial voice and style that AI may have difficulty capturing.



What is it: ChatGPT can cross-reference claims and statements in articles with credible sources and databases to automatically fact-check content.

How it could be done: A GPT model can be trained with pre-processed data from multiple sources. Then it will compare text snippets of a story against the sources, looking for inconsistencies. It can highlight the issues and cite the evidence used to determine them.

How it will help: It will improve the accuracy of news stories and reduce the time and effort required to fact-check manually.

Potential problems: AI cannot always detect nuanced or subjective information, which may require further analysis.


Content recommendation

What is it: ChatGPT can help newsrooms curate and organise their content for their audience. It can also suggest relevant content to readers based on their interests and browsing history.

How it could be done: ChatGPT can analyse users' preferences, browsing history and engagement patterns to recommend relevant news articles. By understanding readers' interests, it can suggest articles based on their past reading habits, topics they follow and trending news stories.

How it will help: It will enhance audience engagement and satisfaction as readers discover content that is aligned with their interests. It will also help the discoverability of content that a reader may have missed otherwise.

Potential problems: The biggest drawback is that excessive personalisation may lead to “filter bubbles” - or “echo chambers” - where people are exposed only to content that aligns with their existing beliefs and not to diverse perspectives.


Sentiment analysis

What is it: GPT models can analyse articles for sentiment to provide insights into public opinion.

How it could be done: AI can learn to identify patterns to examine the overall sentiment of a news piece or a social media post as positive, neutral or negative. It can also take user interactions into consideration and make suggestions to the content writers.

How it will help: It would help newsrooms understand the opinions, reactions and preferences of the audience, help create more balanced pieces and address diverse perspectives.

Potential problems: As GPT models better understand emotions, biases and figurative language, the analysis will also get better. Right now, AI may not be able to detect sarcasm, irony or other nuances that can affect sentiment analysis.


Keyword extraction

What is it: ChatGPT can identify the most important keywords in news articles to help optimise them for SEO.

How it could be done: A GPT model could be trained to recognise important keywords that are related to a news story. It would monitor for accuracy and relevance and then provide recommendations to content writers to help improve an article’s visibility in search engines.

How it will help: It could increase exposure and reach for news organisations.

Potential problems: GPT suggestions must be filtered to ensure they reflect the context of certain keywords.



More Articles

Journalistic malpractice monitoring in Gaza coverage

On this page, the editorial team of the Al Jazeera Journalism Review will collect news published by media institutions about the current war on Gaza that involves disinformation, bias, or professional journalistic standards and its code of ethics.

A picture of the Al Jazeera Media Institute's logo, on a white background.
Al Jazeera Journalism Review Published on: 28 Nov, 2023
Why have opposition parties in India issued a boycott of 14 TV presenters?

Media workers in India argue that boycotts of individual journalists are not the answer to pro-Government reporting bias

Saurabh Sharma
Saurabh Sharma Published on: 23 Oct, 2023
Punishing the popular: the suspension of a youth magazine in Vietnam

Media outlets not directly affiliated with the state are not allowed to produce ‘news’ in Vietnam - but the loose definition of ‘news’ means many fall foul of the rules

AJR Correspondent Published on: 19 Oct, 2023
When journalism and artificial intelligence come face to face

What does the future really hold for journalism and artificial intelligence?

Amira Zahra Imouloudene Published on: 12 Oct, 2023
The bombs raining down on Gaza from Israel are beyond scary, beyond crazy

REPORTER'S NOTEBOOK: As Israel bombarded Gaza for the third night, I found myself closer to a missile hit than I could have imagined

Maram Humaid Published on: 11 Oct, 2023
‘We are not going to stop doing journalism’ - reporters defiant after raids on India’s NewsClick

This week’s raid on the offices and homes of NewsClick employees is the latest in a string of attacks on independent news outlets critical of the Indian government

Saurabh Sharma
Saurabh Sharma Published on: 6 Oct, 2023
The French banlieues and their troubled relationship with the media

Discriminatory media coverage of recent unrest in the suburbs of Paris shows that little has changed since the uprisings of 2005

Ahmed Nazif Published on: 28 Sep, 2023
Why are Zimbabwe’s elections always surrounded by media controversy?

Election season in Zimbabwe has long been shrouded in controversy, with intimidation of opposition activists and journalists, combined with disorganisation at the ballots creating a perfect storm for chaos. This year was no different

Derick M
Derick Matsengarwodzi Published on: 25 Sep, 2023
Analysis: The media’s coverage of the Pakistan cable car incident

It was a roller coaster ride with news organisations all over the world giving minute-by-minute reports on the daring rescue. How does the media create suspense and is this sort of coverage useful?

Anam Hussain
Anam Hussain Published on: 21 Sep, 2023
How to use data to report on earthquakes

Sifting through data sounds clinical, but journalists can use it to seek out the human element when reporting on natural disasters such as earthquakes

Arwa Kooli Published on: 19 Sep, 2023
‘I had no idea how to report on this’ - local journalists tackling climate change stories

Local journalists are key to informing the public about the devastating dangers of climate change but, in India, a lack of knowledge, training and access to expert sources is holding them back

Saurabh Sharma
Saurabh Sharma Published on: 13 Sep, 2023
Ethical reporting - how to cover suicide responsibly

Sensationalist reporting of suicide cases has been shown to cause a rise in the numbers of people taking their own lives in affected communities. Journalists must take great care

Abeer Ayyoub
Abeer Ayyoub Published on: 7 Sep, 2023
‘Don’t let someone else narrate your stories for you’ - travel journalists in the global south

THE LONG READ: Life as a travel journalist isn’t just for privileged Westerners ‘discovering’ quaint parts of south-east Asia and Africa

Anam Hussain
Anam Hussain Published on: 1 Sep, 2023
‘People need to stop blindly obeying the law’ - journalists fighting on the fringes in Vietnam

THE LONG READ: Imprisoned, exiled and forced to base themselves overseas, independent journalists in Vietnam are punished harshly if they publish the ‘wrong’ sort of content. Some, such as Luật Khoa tạp chí, are fighting back

AJR Correspondent Published on: 25 Aug, 2023
Ethics and safety in OSINT - can you believe what you see?

OSINT is increasingly important for journalists in a digital world. We take a look at ethics, safety on the internet and how to spot a ‘deepfake’

Sara Creta Published on: 15 Aug, 2023
‘Other journalists jeer at us’ – life for mobile journalists in Cameroon

Journalists in Cameroon are using their phones in innovative ways to report the news for many different types of media, but major news organisations have still not caught up

Akem Nkwain Published on: 1 Aug, 2023
‘Life of journalists is cheap’ - how the Philippines became deadly for reporters

Forging ahead with a career in journalism is fraught with difficulty in the Philippines - and many are walking away. What went so wrong?

Ana P Santos Published on: 19 Jul, 2023
Analysis: Could AI replace humans in journalism?

Recent advances in AI are mind-blowing. But good journalism requires certain skills which, for now at least, only humans can master

Mei Shigenobu
Mei Shigenobu Published on: 17 Jul, 2023
Understanding the pitfalls of using artificial intelligence in the news room

We’ve all been amazed by new advances in AI for news rooms. But we must also focus on ensuring its ethical use. Here are some concerns to address

Konstantinos Antonopoulos Published on: 10 Jul, 2023
AI in the newsroom - how to prompt ChatGPT effectively

Interested in using ChatGPT in your work as a journalist? Here’s how to do it more efficiently

Konstantinos Antonopoulos Published on: 29 Jun, 2023
Analysis: Comparing coverage of the Titanic submersible and migrant boat disasters

Two disasters costing human lives have occurred at sea in the past two weeks, but the media coverage of each was markedly different. How and why?

Anam Hussain
Anam Hussain Published on: 28 Jun, 2023
What is ChatGPT and why is it important for journalists?

AI is taking the world by storm. In the first of a series of articles about the latest developments, we explain what it's all about

Konstantinos Antonopoulos Published on: 13 Jun, 2023
The silencing of Sudan's journalists - again

THE LONG READ: Detained, beaten and their cameras smashed - Sudan’s journalists are enduring a renewed crackdown on the media

Philip Obaji Jr
Philip Obaji Jr Published on: 7 Jun, 2023
'Rebuilt memory by memory' - recreating a Palestinian village 75 years after the Nakba

REPORTER'S NOTEBOOK: How it took the collective memories of several generations, painstaking interviews and a determined search through tall grass and prickly plants to recreate a destroyed community

Amandas Ong Published on: 4 Jun, 2023