One of the most distinguished features of humanity, is being able to read someone else’s mood. People estimate other peoples mood and emotional state based on their verbal and non-verbal communication. Humans learn this skill from a very early age on and are able to distinguish the signs even for different people. For example, we all know when our best friend is feeling down, even when they’re trying to hide it for others. Maybe by being louder than usual, or they might be more quiet. But you know that they are troubled. Being able to distinguish this for different people is due to experience and how close you are to the other person. The years of friendship make it easier to read her mood and know when something is wrong.
Sentiment analysis
But what if I tell you a computer can also do this? And they don’t have to ‘be your friend’ for years and years. Using various techniques such as Natural Language Processing (NLP), the computer is able to recognise words and sentences as emotions. Words like ‘stress’ and ‘feeling alone’ are registered as negative, whilst ‘glad’ and ‘exited’ as marked as positive. This is called a sentiment analysis. Some sentiment analysis even link certain combinations of words to feelings, such as depressed, sad, cheerful or hopeful.
Possibilities
But what are the possible use cases of the sentiment analysis? And what are the challenges? Sentiment analysis is for example already being used in healthcare. Based on the unstructured notes a psychologist takes during sessions with their client, the sentiment analysis can track the clients mood over time. In this case, it includes possible diagnoses and ‘trigger words’ such as suicidal. This allows the psychologist to have one overview of the client’s emotional and mental state over time.
But what if this is taken one step further. What if this is done based on social media. Think about it: Your stories, chat messages, posts, web usage, emoticon usage, everything is documented and examined on your emotional state.
Challenges
One of the most important questions that arises from this, is regarding to privacy. Who is allowed when to measure your mental state based on your social media usage and your google searches? This is very sensitive (health)data, not stated by a doctor, but estimated by a computer. Another challenge is interpreting the words correctly, for example: ‘good’ is a positive word but ‘really not good’ is a negative combination of words. The complexity of languages can make it hard for a computer to interpret it correctly. However, Artificial Intelligence (AI) is often used for this so that the estimations become more accurate with each analysis.
Sources
Abualigah, L., Alfar, H., Shehab, M., & Hussein, A. (2019). Sentiment Analysis in Healthcare: A brief Review. In M. Abd Elaziz, M. Al-quaness, A. Ewees, & A. Dahou, Recent Advances in NLP: The Case of Arabic Language (pp. 129-141). Switzerland: Springer, Cham. doi:10.1007/978-3-030-34614-0_7
Denecke, K., & Deng, Y. (2015, March 25). Sentiment analysis in medical settings: New opportunities and challenges. Artificial Intelligence in Medicine, pp. 17-27. doi:10.1016/j.artmed.2015.03.006
Interesting article Desiree! I wasn’t that surprised that computers can make sentiment analysis using NLP, it sounds pretty obvious to me. But I agree with you that when algorithms can make these analysis based on your social media usage, it will become much more sophisticated compared to only analyzing words. However, I wouldn’t be surprised if this already happens. Social media companies gather so much data. Emotional analysis and trends could probably already be analyzed with the data, and bought by companies that are interested in that data. Therefore, I completely agree that privacy is the most important topic in this debate (or with almost any debate around social media). I would argue that the only way of escaping this, is not using social media anymore.
Do you think these sentiment analysis based on social media usage are something of the future or that it is already happening? And how can it be used in a correct way?
Hii Bram,
Thank you for your comment. I agree with you that my example of NLP usage was not that surprising, but I wanted to make the article easy enough to read for everyone and didn’t know if this was common knowlegde. However, I do think that NLP is still relevant, ofcourse in combination with other types of data its potential becomes much greater. I agree with you that it is difficult to manage this regards to privacy. I think it is already happening, but probably not at its full potential currently. Social media entails many kinds and types of data (images, gifs, emoticons, stickers, text, boomerangs, videos, audio of voices, audio of music, etc) so I think that it is difficult to combine all these analysis into one conclusion. I think something about this should be included into the GDPR to entail correct use. I would put it in the same category as ‘healthcare data’ and therefore make it very restricted and difficult for facebook (or other social media) to do this
Thanks, Desiree for bringing this concept up. It struck my attention and I went looking on the web to find more information. I do agree with Bram that it is not very surprising that this technology is used in daily life already. It has been a relatively well-established concept for years now. I do like your comment on potential analyses that can be done in the future. The thought of people making analyses based on my social media posts scares me a bit.
I think in the future sentiment analyses will expand its usage beyond text analyses. This post made me search for sentiment analyses based on Naturalistic Video. Imagine that cameras in stores/shops can monitor your reaction to a certain product in the future. Privacy will still be an issue, but the thought of this being (technically) possible is shocking. For this type of sentiment analysis, they are not there yet, but this will come our way.
Hello Maartje,
I totally agree with you. I also find it scary to think that Instagram will know when I smile or ‘fake smile’ in photos, when I feel good or down, and potentially use that to adjust my ads (to ads for products that are my personal ‘weaknesses’ when I’m having a hard time.
I also didn’t think about the potential of sentiment analysis in shops yet, but that is an interesting concept as well. As I stated in my comment to Bram, i think sentiment analysis should get special notion in the GDPR with its risks and therefore be considered as highly sensitive data
Thank you for your comment