I am uncertain about using Artificial Intelligence (AI), like ChatGPT, to produce articles related to occupational health and safety (OHS), but thought I better familiarise myself with the process. So, I asked ChatGPT to
“Create a 400-word document discussing psychosocial hazards in the workplace and the most effective methods to prevent them happening.”
Below is the article and a discussion of its deficiencies:
Psychosocial hazards in the workplace refer to factors that can negatively impact an individual’s psychological and social well-being. These hazards can include stress, bullying, discrimination, and harassment. They can also include factors such as a lack of autonomy, poor communication, and a lack of support. These hazards can lead to a variety of negative consequences for employees, including increased absenteeism, decreased productivity, and even mental health issues. To prevent psychosocial hazards from occurring in the workplace, there are several effective methods that can be implemented.
One of the most effective methods for preventing psychosocial hazards is to promote a positive work culture. This can be achieved by encouraging open communication, fostering a sense of collaboration and teamwork, and providing employees with opportunities for growth and development. Additionally, employers can take steps to ensure that all employees are treated fairly and with respect, and that discrimination and harassment are not tolerated.
Another key method for preventing psychosocial hazards in the workplace is to provide employees with support and resources to help them manage stress and other challenges. This can include things like employee assistance programs, counseling services, and mental health days. Employers can also provide employees with training and education on how to manage stress and maintain good mental health.
Implementing flexible work arrangements, such as remote work, flexible schedules, and job sharing, can also help to prevent psychosocial hazards. Allowing employees to have more control over their work environment and schedule can help to reduce stress and improve overall well-being.
Having a clear and effective complaint and investigation process is also important to preventing psychosocial hazards. This process should be clearly communicated to all employees, and should be fair, impartial, and respectful. Employees should be encouraged to report any concerns they have, and should be informed of the steps that will be taken to address the issue.
In summary, the most effective methods for preventing psychosocial hazards in the workplace include promoting a positive work culture, providing support and resources to employees, implementing flexible work arrangements, and having a clear and effective complaint and investigation process. By taking these steps, employers can create a safer, healthier, and more positive work environment for all employees.
The article is a good summary of psychosocial hazards at work for people outside of the issue. The core deficiency is that the focus on individual interventions dominates. It promotes a positive work culture, and this is important, but that could be nothing more than health promotion which has been in effect for well over a decade without, apparently, reducing psychological harm. Increased awareness may have occurred, but it has not prevented workplace psychological harm.
The article fails to mention COVID and the related anxiety increases, perhaps because work was so disrupted that any psychosocial harm was generated by non-work matters. The AI gets a tick for avoiding the hyperbole and excuses for mental ill-health that many psychology-based are using.
The AI advocates implementing flexible work arrangements, but those have largely been achieved due to anxiety about a pandemic rather than work factors. It could be argued that the way this rapid transition from office- to home-based work was managed created additional anxiety, but the primary reason was to ensure business continuity, not the mental welfare of workers. The research is still out on whether working from home improves or increases psychosocial harm at work. There are indications that the mental anguish from the pandemic is changing to other, new forms of anxiety, such as disengagement, loneliness and isolation.
Flexible work arrangements are also becoming less flexible as the situation normalises.
The OHS context is mostly missing from the AI article. That may be understandable because the OHS context has only recently been given the legitimacy it deserves through inquiries, research, regulation and some enforcement.
And it was 30 words short!
It is highly unlikely that this blog will carry any articles written by Artificial Intelligence, but that cannot be guaranteed for other social media and internet sites. I am already receiving media releases generated by AI and offers to contribute articles from dubious sources that cannot be verified. Between bots and AI, writing on OHS matters is becoming more complex. The best I can do is maintain the humanity of this blog with all its errors, biases, creativity and opinions.
Thanks for the continuing support of our human subscribers.
Thanks for exploring this issue. Have you seen this?
https://theconversation.com/major-publishers-are-banning-chatgpt-from-being-listed-as-an-academic-author-whats-the-big-deal-198765?utm_medium=email&utm_campaign=Latest%20from%20The%20Conversation%20for%20February%201%202023%20-%202531325426&utm_content=Latest%20from%20The%20Conversation%20for%20February%201%202023%20-%202531325426+CID_02fc927c904c025f08dc6c7b5d620a1d&utm_source=campaign_monitor&utm_term=Major%20publishers%20are%20banning%20ChatGPT%20from%20being%20listed%20as%20an%20academic%20author%20Whats%20the%20big%20deal
Fred I agreed. I too have been testing ChatGPT and it provides very basic information. You as the user needed to be knowledgeable on the subject matter, ask the questions and then fill in the gaps.
Yes misses a lot of organisational causes. Safe person approach which has a place but seriously limited from a preventative point of view.
I am curious. If the current WHS regulations, codes and guidance on psychosocial health were uploaded and it was asked to write a new (and better) one, how would it fare?
I wonder if Regulators will attempt to do this in the future as a starting point on developing guidance in new areas.
For example uploading relevant accident descriptions (as set out by courts, coronial inquests, regulator summaries, statistical data, overseas models), and asking the AI to write a draft or a consultation paper.
Obviously it would require detailed human review, but l suspect it will be something which someone will experiment with sooner rather than later.
I suspect this software will replace the need for humans to produce a “rough draft”. But it creates more importance for knowledgeable editors and fact-checking.
Kevin, yes, but an interesting perspective nevertheless.
I’ve been using ChatGPT a bit testing it’s capabilities. Given you have asked it a pretty broad question it has given you a pretty generic answer.
If you run it again asking it to factor in the bits you thought were lacking the answer will improve.
We asked it a generic safety question and felt the same. Went back and refined the question a few times and the answer was unsettlingly accurate and knowledgeable.
It’s “learning” stopped about 2 years ago so anything current won’t be there for it to use for reference, but there is talk the pro version will connect live to the internet.
One area we are thinking will be interesting is if we can load all the organisation WHS policies, procedures, and relevant legislation then ask it how do I questions, or even to look for inconsistenties across the documents.
Upload isn’t working at the moment, but we cut and pasted some documents and it was (again creepily) good at churning through the documents.
Will it replace advisors, or even blog writers 😜, probably not in the near future, but it does have the potential to make life easier.
Greta observations Fred