The six-week course is designed to be adapted by universities and colleges to meet local needs.

It explores modern journalism, focusing on technology, ethics, and media production. Students will examine digital newsgathering, fact-checking, and editorial ethics while analysing misinformation and bias in the news. The course also covers the role of AI and algorithms in shaping journalism. Through a mix of theory and practice, students will gain the skills to navigate and influence the future of digital media.

Week 1: Editorial ethics in the digital age

• Overview:
  • In today’s fast-changing digital media landscape, journalistic ethics face new challenges. In the first week we’ll focus on core values such as accuracy, fairness, and integrity. We’ll examine how these principles apply online, the impact of unconscious bias on news, and the pressures of the digital news cycle. Through readings and discussions, we’ll tackle ethical dilemmas and learn how to uphold high journalistic standards.
• Topics:
  • Ethical principles in digital journalism and their practical applications
  • Ensuring accuracy, fairness, and journalistic integrity in online reporting
  • The role of unconscious bias in shaping media narratives and audience trust
  • Ethical dilemmas in the fast-paced, high-pressure digital news environment
• Essential reading:
  • Why editorial ethics are important
  • Lesson: Editorial ethics
  • Integrity and journalism
  • Lesson: Integrity in journalism
  • Accuracy in journalism
  • Lesson: Accuracy in journalism

Week 2: Digital newsgathering and production

• Overview:
  • The digital revolution has transformed journalism, shifting from traditional reporting to advanced digital production. In the second week you’ll learn how newsrooms adapt to a digital-first world. We’ll explore investigative journalism in a multi-platform environment, advanced storytelling techniques for digital and video formats, and strategies for audience engagement. This week will equip you with the skills to create impactful stories in today’s fast-paced media landscape.
• Topics:
  • The transformation of traditional newsrooms into digital-first operations
  • Investigative journalism in a multi-platform and converged media environment
  • Advanced storytelling techniques for digital, video, and interactive formats
  • Effective strategies for online news prioritization and audience engagement
• Essential reading:
  • Introducing a converged newsroom strategy
  • Lesson: Newsroom convergence
  • Creating a converged news operation
  • Convergence workflows: Roles and responsibilities
  • Lesson: How to construct a TV news package
  • Presenting and exploiting content online
  • How to set online news priorities
  • Managing a news website front page

Week 3: Advanced fact-checking in the digital age

• Overview:
  • As information spreads more rapidly and misinformation is a constant threat, it’s crucial to know how to separate fact from fiction. In the third week we’ll focus on the importance of verification in journalism. You’ll learn ethical fact-checking practices and methods for real-time digital verification. We’ll also cover how to create fact-checking systems and explore how AI is used to detect manipulated content. By the end of the week, you’ll be equipped to defend against misinformation and uphold journalistic integrity.
• Topics:
  • The ethical necessity of rigorous fact-checking in modern journalism
  • Investigative methodologies for real-time digital verification
  • Developing and implementing comprehensive fact-checking frameworks
  • The role of artificial intelligence in detecting misinformation and verifying sources
• Essential reading:
  • Fact-checking and adding context
  • Beyond basic fact-checking
  • Lesson: Beyond basic fact-checking
  • Creating a strong fact-checking system

Week 4: Misinformation, disinformation, and fake news

• Overview:
  • Not only has the digital age enabled information to spread faster, it’s also also made it easier to manipulate, which can have serious social and political effects. In the fourth week we’ll explore the dangers of false information. You’ll learn how to spot and counter disinformation and understand the importance of trust in digital journalism. We’ll also look at the rise of deepfakes and AI-generated content and their impact on public trust. This week will help you navigate the challenges of misinformation in today’s media landscape.treacherous landscape of online deception and learn how to defend the truth in an age of pervasive misinformation.
• Topics:
  • The societal and political ramifications of misinformation campaigns
  • Techniques for identifying and countering disinformation tactics
  • The role of trust chains in digital journalism and credibility assessment
  • The impact of deepfakes and AI-generated content on public trust
• Essential reading:
  • How to identify and deal with fake news
  • Fake news and trust chains
  • Lesson: Fake news
  • Dealing with disinformation and misinformation
  • Information disorder: Mapping the landscape
  • Snacking on rumour, feeding on fact

Week 5: Bias, social media, and audience influence

• Overview:
  • The influence of social media where unverified information spreads at speed, along with algorithms deciding what information is shared, maintaining journalistic integrity is harder than ever. In the fifth week we’ll examine how bias affects news production and trust in media. You’ll learn about the powerful role social media plays in spreading news and shaping how it’s created. We’ll look at audience habits and how their demand for instant, personalised content can impact objective reporting. This week will provide practical strategies for reducing bias and keeping your journalism fair and truthful.
• Topics:
  • The impact of bias in digital journalism and media credibility
  • The influence of social media platforms on news production and dissemination
  • Audience consumption patterns and their implications for journalistic integrity
  • Strategies for mitigating bias and enhancing journalistic objectivity
• Essential reading:
  • • Confronting editorial bias in election coverage
    • Social media in news production and news dissemination
    • Adapting to changing audience behaviour and monitoring the market
    • Unconscious bias and its impact on journalism
    • Lesson: Unconscious bias

Week 6: Artificial intelligence and algorithmic influence in journalism

• Overview:
  • Artificial intelligence is changing journalism. It offers new possibilities and raises new factual and ethical challenges. In the sixth and final week we’ll explore how AI is used in news automation, curation, and investigative reporting. You’ll learn about the practical uses of AI and the ethical concerns, like algorithmic bias. We’ll also examine how machine learning and audience targeting are shaping the future of journalism. This week will give you strategies to maintain journalistic integrity in an AI-driven media world, ensuring truth remains the priority.
• Topics:
  • The expanding role of AI in news automation, curation, and investigative journalism
  • The ethical challenges posed by algorithmic bias and AI-driven reporting
  • The implications of machine learning and audience targeting on journalism’s future
  • Strategies for maintaining journalistic integrity in an AI-driven media landscape
• Essential reading:
  • Artificial intelligence assesses its role in journalism
  • AI and investigative journalism
  • Lesson: AI-powered investigations
  • How to detect AI-generated images
  • Systems thinking for journalists

Coursework and assessement

For coursework and assessment, students are expected to combine the theoretical and practical knowledge gained throughout the six weeks. This includes demonstrating an understanding of ethical considerations in digital journalism, proficiency in digital newsgathering and verification techniques, and the ability to critically analyse the impact of emerging technologies. Assessments will include a combination of written assignments, such as essays and case studies, and practical exercises, such as developing fact-checking frameworks or analysing digital news narratives for bias. Students should be prepared to articulate their perspectives on the future of journalism, considering the interplay of technological advancements, ethical dilemmas, and audience engagement. Ultimately, this course aims to foster informed, ethical, and adaptable journalists capable of upholding journalistic integrity in the rapidly evolving digital age.

The post Module: Digital Journalism first appeared on Media Helping Media.

It is based on the article ‘Dealing with algorithmic bias in news‘, which we recommend trainers read before adapting this outline for your own purposes.

Learning objective

Students will identify and analyse instances of algorithmic bias in news content. They will evaluate the impact of such biases on news quality and credibility, using real-world case studies.

• Student-facing objective: By the end of this lesson the student will be able to spot and assess algorithmic bias in news stories and understand how it affects the news we read and produce.
• Standards: Journalist will learn how to spot and deal with algorithmic bias in news

Learning activities

Warm-up

Display a short news headline generated by an algorithm. Ask students: “What do you notice? What do you wonder?” Give them a few minutes to think and discuss with a partner. Then, select a few students to share their observations and questions. Record these for all to see. Guide the conversation towards recognising potential biases in the headline, such as language choice or topic emphasis. This primes students for deeper exploration of algorithm bias in news.

Direct instruction

• Introduction to algorithmic bias: Explain the concept of algorithmic bias. Define key terms: selection bias, confirmation bias, and representation bias. Use a real example, such as a news recommendation engine that consistently suggests similar types of stories, to illustrate how bias can manifest. Discuss the impact of these biases on news quality and credibility.
• Sources of algorithmic bias: Describe the origins of algorithmic bias. Highlight three main sources: biased data, biased algorithms, and lack of transparency. Provide a case study, such as the Facebook Cambridge Analytica scandal, to demonstrate how biased data can lead to skewed news coverage. Encourage students to consider how transparency in algorithm design could mitigate these issues.
• Case studies and lessons learned: Present a case study where algorithm bias affected news coverage, such as the YouTube algorithm’s role in spreading misinformation. Discuss the lessons learned from this case. Ask students to identify signs of bias and suggest strategies for reducing its impact. Emphasise the importance of human oversight and editorial judgment in balancing algorithmic recommendations with journalistic integrity.

Guided practice

Think, Pair, Share: Guide students through a structured discussion to identify algorithmic bias in news content.

• Think: Present a news article generated by an algorithm. Ask students to individually identify potential biases, focusing on language, source selection, and representation.
• Pair: Have students pair up to discuss their findings. Encourage them to compare observations and refine their understanding of algorithmic bias.
• Share: Facilitate a class discussion where pairs share their insights. Record key points on the board, highlighting common biases and unique observations.
• Connect: Relate the discussion back to the case studies covered in direct instruction. Ask students to connect their findings with real-world examples.
• Reflect: Conclude with a reflection on how recognising algorithmic bias can improve news quality and credibility. Encourage students to consider the role of journalists in mitigating bias.

Independent practice

• Bias detection exercise: Provide students with a set of news articles generated by algorithms. Instruct them to identify and annotate instances of potential bias, focusing on language, source selection, and representation. Use a digital tool or printed copies for annotations.
• Analysis and reflection: Ask students to write a brief analysis of their findings, discussing the impact of identified biases on news quality and credibility. Encourage them to propose strategies for mitigating these biases.
• Peer review: Pair students to exchange their analyses. Have them provide constructive feedback on each other’s work, focusing on the clarity of bias identification and the feasibility of proposed strategies.

Assignment

Ask students:

1. What is one example of algorithmic bias you identified in today’s lesson?
2. How can journalists help mitigate algorithmic bias in news content?
3. What’s one question you still have from today’s lesson?

Suggested answers:

• Suggested answer to Question 1: An example is the YouTube algorithm promoting misinformation by favouring sensational content.
• Suggested answer to Question 2: Journalists can advocate for transparency in algorithm design and apply human oversight to ensure balanced news coverage.

Teacher resources

Differentiation guide

• Advanced learners: Encourage deeper analysis by having them explore additional case studies or research articles on algorithmic bias. Challenge them to propose innovative solutions for mitigating bias, considering ethical implications and technological advancements.
• Striving learners: Simplify concepts by using more relatable examples and providing additional scaffolding, such as graphic organisers or guided notes. Offer more structured support during activities, such as pairing them with peers who can assist in discussions and exercises.
• Recommended reading: This lesson plan is based on the article ‘Dealing with algorithmic bias in news‘, which we recommend trainers read before adapting this outline for your own purposes.

Notable definitions

Algorithmic bias: The systematic and repeatable errors in a computer system that create unfair outcomes, such as privileging one arbitrary group of users over others.

Selection bias: A type of bias caused by selecting non-random data for analysis, which can lead to inaccurate conclusions.

Confirmation bias: The tendency to favour information that confirms existing beliefs or hypotheses, often leading to skewed data interpretation.

Required materials

• Computers: For accessing digital news articles and annotation tools.
• Printed copies: News articles for annotation exercises (optional).
• Digital annotation tools: Software or apps for marking up digital articles.
• Whiteboard/Markers: For recording observations and discussion points.
• Projector: To display news headlines and case studies.
• Notebooks/Pens: For students to take notes and write reflections.

Lesson summary

• Warm-up
• Direct instruction
• Guided practice
• Independent practice
• Assignment

The free teaching tools at the Khan Academy were used in the production of this lesson plan.

Related article

Dealing with algorithmic bias in news

The post Lesson: Algorithmic bias first appeared on Media Helping Media.

Journalists need to be trained in how to recognise and deal with algorithmic bias in order to counter the speed and scale at which biased content spreads.

That’s the view of Gemini, the artificial intelligence (AI) conversation tool, which says that the need for such training is “more urgent than ever”.

According to AI:

“the rapid advancement of artificial intelligence and machine learning has led to a significant increase in the use of algorithms in news production…

… algorithms can introduce bias into news content, which can have serious consequences for both individuals and society.”

Media Helping Media (MHM) asked Gemini how journalists can recognise and deal with algorithmic bias.

We also asked it to design a one-day training course to equip journalists with the tools they need to tackle the issue.

The following is the text of that conversation, which took place in September 2024. During the conversation Gemini states that while the challenge of bias in news production is not entirely new, the rise of AI has made it more urgent and complex.

AI warns that:

“journalists and news organisations must adapt to this new reality by developing strategies to mitigate algorithm bias and ensure that the news they produce is fair, accurate, and representative”.

We then asked AI the following questions. The answers were immediate. Gemini’s responses are unedited other than to change them from American English to English English  (MHM’s preferred house style).

MHM: What is algorithmic bias in news production?

Gemini AI: Algorithmic bias in news production refers to the unintentional or intentional bias introduced into news content by the algorithms used to curate, personalise, or generate news. This bias can manifest in various ways, including:

• Selection bias: Algorithms may prioritise certain stories or topics over others, leading to a skewed representation of the news.
• Confirmation bias: Algorithms may reinforce existing beliefs or biases by recommending content that aligns with a user’s preferences.
• Representation bias: Algorithms may underrepresent certain groups or perspectives, leading to a lack of diversity in the news.
• Amplification bias: Algorithms may amplify certain narratives or misinformation, contributing to the spread of false or misleading information.

Factors contributing to algorithmic bias:

• Biased data: If the data used to train algorithms is biased, the algorithms will likely produce biased outputs.
• Biased algorithms: The design of algorithms themselves can introduce bias, such as by prioritising certain features or metrics over others.
• Lack of transparency: The lack of transparency in how algorithms work can make it difficult to identify and address bias.

Addressing algorithmic bias in news production requires a multi-faceted approach, including:

• Improving data quality: Ensuring that the data used to train algorithms is diverse, representative, and free from bias.
• Designing unbiased algorithms: Developing algorithms that are transparent, accountable, and resistant to bias.
• Promoting transparency: Increasing transparency in how algorithms are used and the decisions they make.
• Human oversight: Ensuring that human editors and journalists play a role in reviewing and curating news content.

By understanding and addressing algorithmic bias, news organisations can help to ensure that the news they produce is fair, accurate, and representative.

MHM: How can journalists avoid algorithmic bias if they are not in control of the algorithms?

Gemini AI: While journalists may not have direct control over the algorithms used in news production, they can take several steps to mitigate algorithmic bias:

1. Be aware of algorithmic bias: Journalists should understand the concept of algorithmic bias and how it can manifest in news content. This knowledge can help them identify potential biases and take steps to address them.
2. Critically evaluate news sources: Journalists should be sceptical of news stories generated or curated by algorithms. They should carefully evaluate the sources of information and verify the accuracy of the content.
3. Seek diverse sources: Journalists should strive to gather information from a variety of sources, including those that may not be prominently featured in algorithm-driven news feeds. This can help to ensure that the news they report is balanced and representative.
4. Use human judgement: Journalists should rely on their own judgement to assess the quality and relevance of news stories. They should be willing to override algorithmic recommendations if they believe that they are biased or misleading.
5. Advocate for transparency: Journalists can advocate for greater transparency in how algorithms are used in news production. This can help to identify and address biases and ensure that the news is produced in a fair and ethical manner.
6. Collaborate with data scientists: Journalists can collaborate with data scientists to understand how algorithms work and identify potential biases. This can help them to develop strategies for mitigating algorithm bias.

By taking these steps, journalists can help to ensure that the news they report is accurate, balanced, and free from algorithmic bias.

MHM: So mitigating algorithmic bias is a new task brought about by the advance of AI but should now become a crucial part of a news producer’s job?

Gemini AI: That’s a great observation. While the term ‘algorithmic bias’ may be relatively new, the underlying issue of bias in news production has existed for centuries. However, the advent of AI and machine learning has amplified the potential for bias to be introduced into news content at a larger scale and at a faster pace.

Here’s a breakdown of how traditional news production compared to AI-driven news:

Traditional news production:

• Human curation: News editors and journalists manually select and curate stories based on their judgement and expertise.
• Limited reach: News distribution was primarily through print and broadcast media, limiting the audience and potential for bias.

AI-driven news production:

• Algorithmic curation: Algorithms use data to recommend news stories to users, often based on their past behaviour and preferences.
• Vast reach: News can be disseminated instantly to a global audience through digital platforms, increasing the potential impact of bias.

Key differences:

• Scale: AI can process and analyse vast amounts of data, increasing the potential for bias to be introduced at a larger scale.
• Speed: AI can disseminate news at a much faster pace than traditional methods, making it difficult to identify and correct biases before they have a significant impact.
• Personalisation: AI can personalise news content to individual users, potentially reinforcing existing biases and limiting exposure to diverse perspectives.

Therefore, while the challenge of bias in news production is not entirely new, the rise of AI has made it more urgent and complex. Journalists and news organisations must adapt to this new reality by developing strategies to mitigate algorithmic bias and ensure that the news they produce is fair, accurate, and representative.

MHM: So would you say that dealing with algorithmic bias should now be part of every journalist’s basic training?

Gemini AI: Absolutely. Dealing with algorithmic bias should be a fundamental part of every journalist’s training in the digital age. Here’s why:

1. Understanding the problem: Journalists need to understand how algorithms work, how they can introduce bias, and the potential consequences of this bias.
2. Identifying and mitigating bias: Journalists should be able to identify signs of algorithmic bias in news content and take steps to mitigate its effects.
3. Evaluating sources: Journalists should be able to critically evaluate the sources of information they rely on, especially those that are generated or curated by algorithms.
4. Promoting diversity and inclusion: Journalists should strive to promote diversity and inclusion in the news they report, by seeking out a variety of sources and avoiding algorithmic biases that may underrepresent certain groups or perspectives.
5. Advocating for transparency: Journalists can advocate for greater transparency in how algorithms are used in news production, which can help to identify and address biases.

By incorporating training on algorithmic bias into journalism programmes, we can equip journalists with the skills and knowledge they need to produce fair, accurate, and representative news in the digital age.

MHM: Would you say that the need for journalists to be trained in dealing with algorithmic bias is urgent?

Gemini AI: Absolutely. The need for journalists to be trained in dealing with algorithmic bias is more urgent than ever. The rapid advancement of artificial intelligence and machine learning has led to a significant increase in the use of algorithms in news production. These algorithms can introduce bias into news content, which can have serious consequences for both individuals and society.

Here are some reasons why this training is urgent:

• Increasing reliance on algorithms: News organisations are increasingly relying on algorithms to curate, personalise, and generate news content. This means that the potential for algorithmic bias to impact news coverage is growing.
• The potential for harm: Algorithmic bias can lead to the spread of misinformation, the amplification of harmful stereotypes, and the underrepresentation of certain groups or perspectives. This can have serious consequences for individuals and society.
• The need for accountability: Journalists have a responsibility to ensure that the news they report is accurate, fair, and unbiased. This includes understanding and addressing the potential for algorithmic bias.

By training journalists in how to identify and mitigate algorithmic bias, we can help to ensure that the news we consume is reliable and trustworthy.

MHM’s conclusion

The fact that AI is warning that journalists need to be trained in recognising and dealing with algorithmic bias suggests that human judgement, journalistic ethics and editorial values are crucial in a world where artificial intelligence and machine learning is crafting so much content.

As Gemini says in the interview above, “the underlying issue of bias in news production has existed for centuries. However, the advent of AI and machine learning has amplified the potential for bias to be introduced into news content at a larger scale and at a faster pace.”

Questions

1. What is algorithmic bias in news production, and how can it manifest in news content?
2. Identify and describe two factors that contribute to algorithmic bias in news production.
3. Explain why the rise of AI has made the challenge of bias in news production more urgent and complex.
4. What are some steps journalists can take to mitigate algorithmic bias, even if they do not control the algorithms?
5. Discuss the role of human oversight in addressing algorithmic bias in news production.
6. How does algorithmic curation differ from traditional human curation in news production?
7. Why is it important for journalists to seek diverse sources when reporting news?
8. Evaluate the potential consequences of algorithmic bias on society and individuals.
9. How can journalists advocate for greater transparency in the use of algorithms in news production?
10. In what ways can collaboration between journalists and data scientists help address algorithm bias?

Answers

1. Algorithmic bias in news production refers to the unintentional or intentional bias introduced into news content by algorithms. It can manifest as selection bias, confirmation bias, representation bias, or amplification bias.
2. Two factors contributing to algorithmic bias are biased data, where the data used to train algorithms is biased, and biased algorithms, where the design of algorithms prioritises certain features or metrics over others.
3. The rise of AI has made bias in news production more urgent and complex due to the increased scale and speed at which AI can process and disseminate news, as well as the potential for personalised content to reinforce existing biases.
4. Journalists can mitigate algorithmic bias by being aware of it, critically evaluating news sources, seeking diverse sources, using human judgment, advocating for transparency, and collaborating with data scientists.
5. Human oversight involves journalists and editors reviewing and curating news content to ensure it is fair, accurate, and representative, thus helping to identify and correct algorithmic biases.
6. Algorithmic curation uses data to recommend news stories based on user behaviour and preferences, while traditional human curation relies on the judgment and expertise of news editors and journalists.
7. Seeking diverse sources is important to ensure balanced and representative news coverage, avoiding the reinforcement of biases that may underrepresent certain groups or perspectives.
8. Algorithmic bias can lead to the spread of misinformation, amplification of harmful stereotypes, and underrepresentation of certain groups, which can have serious consequences for individuals and society.
9. Journalists can advocate for transparency by pushing for clear explanations of how algorithms are used in news production and the criteria they use for decision-making.
10. Collaboration with data scientists helps journalists understand how algorithms work and identify potential biases, allowing them to develop strategies to mitigate algorithmic bias.

Lesson plan for trainers

If you are a trainer of journalists we have a free lesson plan: ‘Algorithmic bias’ which you are welcome to download and adapt for your own purposes.

The post Dealing with algorithmic bias in news first appeared on Media Helping Media.