Artificial intelligence is changing how students encounter history. Instead of simply reading about Winston Churchill, Rosa Parks, or the Industrial Revolution, students can now explore the past by asking questions to AI-generated representations of historical figures.

Imagine a student interviewing a factory worker in nineteenth-century Britain, questioning a civil rights activist in 1960s America, or discussing a difficult wartime decision with a simulated political leader. These conversations can make history feel more immediate and encourage students to explore perspectives they might otherwise overlook.

But they also raise an important educational question: How can we ensure that students learn to investigate history rather than simply believe what an AI character tells them?

AI historical role-play has educational potential, but only when it is designed around evidence, critical thinking, and teacher guidance. The goal should not be to recreate the past perfectly. It should be to help students develop the skills needed to question historical claims and construct their own interpretations.

Platforms such as Parlova.org are exploring this approach by allowing students to investigate historical questions through conversations with AI-generated characters, while giving teachers the tools to guide and monitor the learning process.

Here are five practical approaches teachers can use.

1. Start With a Historical Mystery, Not a Conversation

One common mistake when introducing AI historical characters is to let students chat without a clear objective.

Although an open conversation can spark curiosity, it does not necessarily lead to meaningful historical understanding.

A better approach is to begin with an enquiry question.

For example:

• Why did some American colonists support independence while others remained loyal to Britain?
• What motivated individuals to participate in the American civil rights movement?
• How did the Industrial Revolution change the lives of factory workers and their families?

Students can then interview simulated historical figures to gather possible explanations.

For a lesson about the American Revolution, one group might question a Patriot merchant, while another interviews a Loyalist or a British official.

Their task is not simply to collect answers. It is to understand why people living through the same events could interpret them so differently.

This transforms the activity from casual conversation into a structured investigation. Students have a problem to solve, competing perspectives to explore, and conclusions to justify.

The teacher’s role is to establish the historical question and explain what constitutes a convincing, evidence-based answer.

2. Treat Every AI Answer as a Claim to Investigate

An AI-generated historical character may sound persuasive, confident, and historically informed. But that does not make its statements reliable.

Language models can produce factual errors, invent details, or present contested interpretations as established facts.

Rather than hiding this limitation, teachers can turn it into an educational opportunity.

After receiving an answer, students can ask themselves:

• What factual claims did the character make?
• Which claims can be verified?
• What evidence would support or contradict them?
• Is the character expressing a particular perspective or describing an established fact?

For example, a simulated Winston Churchill might offer a convincing explanation of a controversial wartime decision. Students should then compare that explanation with contemporary speeches, government records, and historians’ interpretations.

The comparison might reveal that the character has simplified a complex situation, omitted important context, or attributed motives that historians continue to debate.

This distinction is essential: An AI character is a learning simulation, not a primary historical source.

Even when its answers are accurate, they are generated from a modern computational model rather than recovered directly from the past.

The most valuable part of the exercise may therefore be the moment when students discover that a plausible answer is not necessarily a correct one.

3. Introduce Contradictory Perspectives

History rarely provides a single, uncontested interpretation of events.

AI role-play can help students explore this complexity by presenting different historical viewpoints.

Consider a lesson about the Industrial Revolution.

Students might question a factory owner, a textile worker, and a social reformer, each responding from a different economic or social perspective.

A factory owner might emphasise economic growth and technological progress, while a worker might describe long working hours, unsafe conditions, and the challenges of urban life.

A reformer might focus on child labour, education, and the need for new legislation.

Students can compare these arguments and identify the interests, assumptions, and historical circumstances behind them.

The same approach could be used to investigate the American civil rights movement, European colonial expansion, or the social consequences of industrialisation in different parts of the world.

However, teachers should distinguish between historically documented viewpoints and dialogue invented by the AI to illustrate them.

The objective is not to pretend that we can recover exactly what historical people would have said. It is to explore perspectives grounded in historical evidence while recognising the limitations of simulation.

This approach also helps students understand that disagreement does not mean all interpretations are equally well supported.

4. Give Teachers Visibility Into the Investigation

AI tools are sometimes presented as independent tutors capable of replacing direct teacher involvement.

For historical enquiry, that would miss an important part of the educational process.

Teachers need to understand not only what conclusions students reach, but also how they reach them.

Did a student ask relevant questions? Did they challenge a suspicious answer? Did they distinguish between evidence and interpretation? Were they misled by an invented historical detail?

These observations can reveal misconceptions that might otherwise remain invisible.

This is one of the principles behind Parlova, a classroom platform that lets students investigate historical questions through conversations with AI-generated characters.

Teachers can create guided missions, follow students’ conversations in real time, and review their responses afterwards. The platform also provides information about student progress and answers, helping teachers identify which ideas have been understood and which may require further discussion.

For example, if several students accept the same inaccurate claim about the causes of the First World War, the teacher can revisit that point collectively and examine the historical evidence.

Instead of simply marking answers as correct or incorrect, the teacher can use the activity to understand how students reasoned and where their interpretations diverged.

The technology becomes a way to make students’ thinking more visible, rather than a substitute for teaching.

5. Finish With an Evidence-Based Debrief

A successful historical role-play should not end when the conversation ends.

The final stage is where students transform their exploration into historical understanding.

One simple activity is to ask each student or group to produce a short conclusion answering the original enquiry question.

Their answer should include three elements:

1. A clear historical claim.
2. Evidence supporting that claim.
3. An explanation of any uncertainty or competing interpretation.

For example, after investigating working conditions during the Industrial Revolution, students might be asked:

“Did industrialisation improve the lives of ordinary people?”

Different groups may reach different conclusions depending on the period, region, and social group they investigated.

One group might emphasise rising production and long-term improvements in living standards. Another might focus on dangerous working conditions, child labour, and overcrowded cities.

The teacher can then ask students to defend their interpretations using historical evidence rather than relying on what their AI characters said.

Which students consulted additional sources? Which relied too heavily on the simulation? Did different groups reach different conclusions, and why?

A classroom discussion can highlight both sound historical reasoning and the limitations of generative AI.

This also creates an opportunity to teach broader digital literacy skills that extend beyond history: evaluating sources, questioning confident assertions, and recognising uncertainty.

From Historical Simulation to Historical Thinking

AI historical role-play is not valuable simply because students can talk to a simulated historical figure.

Its educational potential comes from what students do with that interaction.

When teachers provide a clear enquiry question, encourage source verification, introduce competing perspectives, and organise a structured debrief, AI dialogue can become a starting point for meaningful historical investigation.

This approach still requires careful evaluation. Engaging activities do not automatically produce better learning outcomes, and the effectiveness of AI-supported historical enquiry needs to be tested in real classrooms.

Nevertheless, the underlying educational principle is straightforward: students should learn to question the information they receive, including information produced by artificial intelligence.

Perhaps the most useful question we can teach students to ask an AI historical character is not simply, “What happened?”

It is: “How do we know?”

Quentin Kral is an astrophysicist at the Paris Observatory and the founder of Parlova, the platform mentioned in this article.

With all the focus schools have on digital technology use (BYOD, Flipped Learning, etc.), it is important that students develop their digital literacy, to use these tools appropriately and responsibly.  For schools using Google Apps for Education, a free online project-based video curriculum has been created to help teach and learn practical digital skills.

1. Go to the Applied Digital Skills site and sign up.

2. Once you’re signed up as a teacher, you can share with your students the self-paced lessons via your Google Classroom.  I have picked out these links below, which are particularly useful for helping students to develop their online research and presentation skills using Google Apps for Education:

Research and Develop a Topic

Create a Presentation All About a Topic

Organise Files in Drive

Create a Photo Journal in Google Docs

The Common Sense Media site for educators (https://www.commonsense.org/education/) also has access to a range of relevant resources and lesson plans for teaching students about digital literacy and citizenship.

Minecraft is what is known as a ‘sandbox’ or ‘open world’ video game in which players roam and create within a virtual world.  Players walk around, jump, dig and punch things with their hand as they build, mine or farm resources.  By allowing users to build and explore as they choose, Minecraft can be used as an immersive learning platform to extend and enrich the curriculum.  For most educators the use of Minecraft might seem like an intimidating idea, especially since many students are experts with this platform!  Nevertheless, the skills and knowledge that students can bring to Minecraft should be seen as benefit.

In all the lessons that I have taught using Minecraft for example, students are very engaged and work collaboratively on the tasks set.  However, no matter what their skill level might be, it’s important to communicate some ground rules beforehand related to digital citizenship, i.e. about behaving appropriately in a digital space.  Just as students would follow rules about how to behave in the real world, they should understand that similar rules apply in their Minecraft world.  They should not, for instance, damage one another’s building efforts, nor should they communicate online (using Minecraft’s chat function) in a way that is inappropriate.

Fortunately, since 2011, MinecraftEdu has been developed specifically for use in the classroom context.  The MinecraftEdu platform retains the key elements of the original Minecraft while including additional features that facilitate its use in the classroom.  Key additional features allow the teacher to control what students are doing in the Minecraft world.  Students can be muted or frozen, for example.  In so doing, MinecraftEdu platform can be used to teach a range of skills and subjects from maths to humanities and social sciences.

Below, I have attached a PDF of the lesson plans that can be used to teach students about building an environmentally friendly city, which we used for our IPC unit on Climate Control.  These lesson plans can easily be adapted for literacy, to help spark students’ imagination.  For example, following Mr P’s lesson ideas, we also got our students designing Kensuke’s Kingdom using Minecraft.  Once students had completed their collaborative virtual kingdom, they were asked to take screenshots and upload these screenshots to their digital portfolios.  This is particularly useful for promoting students’ creative writing skills, as they can then be asked to write a description of the world they have created.

[embeddoc url=”https://technologyforlearners.com/wp-content/uploads/2017/11/Class-4-Building-an-Environmentally-Friendly-City-Minecraft.pdf”]

In his book, The Filter Bubble, Pariser (2011) describes a digital situation we all now face in which website algorithms selectively present information to users based on location, click behaviour, search history, etc., and, as a result, distance users from information that disagrees with their viewpoints, effectively isolating them in their own cultural or ideological bubbles.  In December 2009, for example, Google began using 57 different signals – everything from a user login location to their browser to their search history – to make guesses about who the user is and what kinds of sites the user would like to see.  Likewise, social networking sites such a Facebook and Twitter are built on the premise that users interact with other users that they have chosen to interact with, which limits the coverage of news they receive.  Although filter bubbles almost certainly provide users with information of subjective value, based on their needs, desires and preferences, they also lead users to a state of cognitive bias.  This means users may dismiss otherwise potentially useful information, because it does not conform to their cognitive schema.  As more users discover news through algorithm-determined feeds, important news content relevant to the public sphere falls out of view.

According Pariser (2011, pp. 4): ‘Democracy requires citizens to see things from one another’s point of view, but instead we’re more and more enclosed in our own bubbles’. 

In order to be news literate on a global scale, it is surely necessary to break out of these filter bubbles by reading from a wider variety of sources from around the world.

Another type of filter bubble can be seen in terms of the coverage of global news itself.  Reese (2011, pp. 5) states that against the expectation that media report and reach the entire globe, the global media system, particularly international broadcasting, does not live up to that hope.  For example, Alisa Miller, head of Public Radio International, presented a cartogram during a TED Conference to show how the US media covers international news.

Fig. 1

This map shown in Figure 1 represents the number of seconds US network and cable news organisations dedicated to news stories by country in February 2007.  This was a month when there had been very significant international events: North Korea agreed to dismantle its nuclear facilities, there was massive flooding in Indonesia, and the Intergovernmental Panel on Climate Change (IPCC) released a study confirming man’s impact on global warming.  During this month though, Miller (2007) observes the US accounted for 79% of the total news coverage; the combined coverage of China, India, and Russia represented just 1% of the news.  Similar distortions in the way news is covered can be seen in elite online newspapers such as the New York Times and Guardian.

What the cartogram serves to illustrate is that, contrary to what people might think, news media does not deliver an equitable distribution of global news coverage.  According to Adams and Ovide (2009), the online availability of news and the demand for larger corporate profits has driven both audiences and advertisers to cyberspace, triggering a crisis in the news industry, which is increasingly turning to local coverage.  Consequently, foreign news bureaus have been disappearing, as foreign correspondents are seen at best as unnecessary “middle men”, at worst as “endangered species”. (Hamilton, 2009, pp. 463).

Fig. 2

As Figure 2 illustrates, the same problem can be seen on the demand side for news. On average, more than 95% of national news readership is on domestic sites.  Citizens in the UK, for example, are unlikely to read about news happening in Australia on an Australian website.  Instead, they are far more likely to read about events in Australia, filtered through a UK news outlet, such as the Guardian.  Language can be an obvious barrier here, preventing readers from visiting foreign news sites.  With relatively high numbers of immigrants, this may explain why the US and UK have comparatively more of their citizens viewing foreign web pages than China, for instance, which has proportionally fewer immigrants.

Nonetheless, the fact that the vast majority of page views are on domestic news sites for all countries is considered by Zuckerman (2010) to be a serious problem:

‘The real problems in the world are global in scale and scope; they require conversations to get to global solutions.  This is a problem we have to solve’. 

Moreover, when foreign news is reported by a domestic outlet, true comparative analysis is rare. News, according to Reese (2012, pp. 2), is ‘still domesticated through national frames of references, often taken for granted, and media globalisation skeptics have argued that no truly transnational news platforms have emerged, permitting the kind of cross-boundary dialogs associate with a public sphere’.  Media sceptics such as Hafez (2007) point to the continued weaknesses of international reporting: ‘elite-focused, conflict-based, and driven by scandal and the sensational, leading them to conclude that the “global village” has been blocked by domestication’.

As so much of our news now comes from online sources, we need to ensure that our students have the digital literacy skills needed in order to become well-informed global citizens.  If they lack these skills, then we cannot truly claim to be providing an education that facilitates the often touted ideal of “international mindedness”.

References:

Adams and Ovide.  2009.  Newspapers Move to Outsource Foreign Coverage.  The Wall Street Journal, 15 January.

Hafez, K. 2007. The myth of media globalization. Malden, MA: Polity.

Hamilton, J.  2009.  Journalism’s Roving Eye: a history of American foreign reporting, Baton Rouge: Louisiana State University Press

Pariser, E.  2011.  The Filter Bubble: How the New Personalized Web Is Changing What We Read and How We Think.  Penguin Press.

Miller, A.  2007.  Ted Talk: The News about the News.  http://www.ted.com/talks/alisa_miller_shares_the_news_about_the_news.

Reese, S.  2012.  Global News literacy: The Educator.  Global News literacy: The Educator (Chapter prepared for News literacy: Global perspectives for the newsroom and the classroom). University of Texas at Austin.

Zuckerman, E.  2010.  Ted Talk: Listening to Global Voices.  http://www.youtube.com/watch?v=vXPJVwwEmiM

The global news landscape has changed dramatically in recent years. News readership has increasingly shifted to the Internet because of inexpensive technology, ubiquitous access and free content. This has led to a trend of information democratisation in which information control has shifted from a few powerful entities toward smaller outlets and individual citizens. User-generated news sources like blogs, wiki pages and YouTube videos are now commonplace. As a result, according to the Pew Research Center (2012), the audience for news on the Internet has grown from nothing in 1993 to second behind only television.

Although the Internet brings users more news, there is consequently more uncertainty about whether news sources – both traditional and otherwise – are providing relevant or even credible information. Powers (2010, pp. 5), for example, states that young people in particular, report being overwhelmed by the amount of news sources and content available online. This makes it increasingly important for news consumers to develop digital literacy skills that allow them to weigh the value of what they read, see, and hear.

News literacy, a fundamental yet too often unrecognised area of digital literacy, helps students to foster a more intellectually rigorous relationship with news media. News literacy is neatly defined by Schwarz (2011, pp. 1) as ‘the reader’s ability to critically evaluate, interpret and process as well as participate in news media’. As we live in an increasingly interconnected and globalised world, I would argue that the word “global” should also be used when discussing news literacy; much of the news content viewed online is from international journalism networks, which create what Reese (2012) refers to as a “global news arena”. Reese explains that bringing a global perspective to news literacy requires a basic awareness of how national contexts differ; it means taking concrete local circumstances into account while being aware of how they differ from other areas and how global forces bring “influence from a distance”.

Global news is a highly complex, albeit important subject. In my context of working as teacher in a bi-lingual British school in El Salvador, I have seen the importance of this subject manifest in the overall objectives of the International Primary Curriculum (IPC) and International Baccalaureate (IB). These programmes correctly consider themselves to be leading proponents of international education and are designed to promote international mindedness (Stagg, 2013). Students on the IB for example, are required to keep up-to-date with current national and international news events relevant to their areas of study. Moreover, one of the traits and values of the school is “international mindedness”, encouraging students to develop a cosmopolitan attitude and willingness to learn about life in other parts of the world. All of this forms part of the Council of International Schools (CIS) accreditation process, which asks schools to ‘demonstrate a commitment to internationalism in education’ (CIS, 2013).

Unfortunately, despite the buzz words in the curriculum and the rhetoric of schools, little is actually done to facilitate learning about the world in which we live. Specifically, the most relevant sources for informing students (and their teachers) about social, economic and political events happening around the world – global news media – are widely absent from the classroom. This seems to be the case in educational institutions around the world (Stagg, 2013; Schwarz, 2012; Buckingham, 2003).

In July, 2013 I therefore began putting together designs for the user interface of what would become News on Atlas, a web application with the purpose of addressing this issue. I have been working closely with a programmer, Daniel Rivas, to develop the functionality of this application, while ensuring that it is easy to use and runs smoothly. Since its inception, the objective driving this application’s development has remained unchanged – to improve users’ global news literacy. This is an important area of international mindedness and, in my opinion, should be taught in schools alongside digital literacy.

References:

Buckingham, D. 2003. Media Education. Literacy, Learning and Contemporary Culture. Polity Press, USA

Pew Research Center. 2012. http://www.journalism.org/2012/10/25/social-media-doubles-remains-limited/

Powers, E. 2010. Teaching News Literacy in the Age Of New Media: Why Secondary School Students Should Be Taught to Judge the Credibility of the News They Consume. Washington University in St. Louis. http://openscholarship.wustl.edu/cgi/viewcontent.cgi?article=1454&context=etd

Reese, S. 2012. Global News literacy: The Educator. Global News literacy: The Educator (Chapter prepared for News literacy: Global perspectives for the newsroom and the classroom). University of Texas at Austin. http://journalism.utexas.edu/sites/journalism.utexas.edu/files/attachments/reese/educator-chapter-final.pdf

Schwarz, F. 2011. Media Literacy and the News. Windesheim School of Media in Zwolle, the Netherlands. http://www.windesheim.nl/~/media/files/windesheim/research%20publications/120319_media_literacy_and_the_news.pdf

Stagg, L. 2013. International Mindedness: Global Perspectives for Learners and Educators. Urban Publications Ltd.