Artificial intelligence (AI) has begun to permeate many facets of the human experience. AI is not just a tool for analyzing data—it’s transforming the way we communicate, work and live. From ChatGPT through to AI video generators, the lines between technology and parts of our lives have become increasingly blurred.

But do these technological advances mean AI can identify our feelings online?

In our research published in the International Journal of Market Research, we examined whether AI could detect human emotions in posts on X (formerly Twitter).

Our research focused on how emotions expressed in used posts about certain non-profit organizations can influence actions such as the decision to make donations to them at a later point.

Using emotions to drive a response

Traditionally, researchers have relied on sentiment analysis, which categorizes messages as positive, negative or neutral. While this method is simple and intuitive, it has limitations.

Human emotions are far more nuanced. For example, anger and disappointment are both negative emotions, but they can provoke very different reactions. Angry customers may react much more strongly than disappointed ones in a business context.

To address these limitations, we applied an AI model that could detect specific emotions—such as joy, anger, sadness and disgust—expressed in tweets.

Our research found emotions expressed on X could serve as a representation of the public’s general sentiments about specific non-profit organizations. These feelings had a direct impact on donation behavior.

Detecting emotions

We used the “transformer transfer learning” model to detect emotions in text. Pre-trained on massive datasets by companies such as Google and Facebook, transformers are highly sophisticated AI algorithms that excel at understanding natural language (languages that have developed naturally as opposed to computer languages or code).

We fine-tuned the model on a combination of four self-reported emotion datasets (over 3.6 million sentences) and seven other datasets (over 60,000 sentences). This allowed us to map out a wide range of emotions expressed online.

For example, the model would detect joy as the dominant emotion when reading a X post such as, “Starting our mornings in schools is the best! All smiles at #purpose #kids.”

Conversely, the model would pick up on sadness in a tweet saying, “I feel I have lost part of myself. I lost Mum over a month ago, Dad 13 years ago. I’m lost and scared.”

The model achieved an impressive 84% accuracy in detecting emotions from text, a noteworthy accomplishment in the field of AI.

We then looked at tweets about two New Zealand-based organizations—the Fred Hollows Foundation and the University of Auckland. We found tweets expressing sadness were more likely to drive donations to the Fred Hollows Foundation, while anger was linked to an increase in donations to the University of Auckland.

Ethical questions as AI evolves

Identifying specific emotions has significant implications for sectors such as marketing, education and health care.

Being able to identify people’s emotional responses in specific contexts online can support decision makers in responding to their individual customers or their broader market. Each specific emotion being expressed in social media posts online requires a different reaction from a company or organization.

Our research demonstrated that different emotions lead to different outcomes when it comes to donations.

Knowing sadness in marketing messages can increase donations to non-profit organizations allows for more effective, emotionally resonant campaigns. Anger can motivate people to act in response to perceived injustice.

While the transformer transfer learning model excels at detecting emotions in text, the next major breakthrough will come from integrating it with other data sources, such as voice tone or facial expressions, to create a more complete emotional profile.

Imagine an AI that not only understands what you’re writing but also how you’re feeling. Clearly, such advances come with ethical challenges.

If AI can read our emotions, how do we ensure this capability is used responsibly? How do we protect privacy? These are crucial questions that must be addressed as the technology continues to evolve.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

In September, the Purdue University/CME Group Ag Economy Barometer recorded its lowest readings since March 2016. Declining income expectations pushed farmer sentiment down as the barometer fell 12 points to 88, and the Index of Future Expectations dropped 14 points to 94. The Index of Current Conditions also fell 7 points to 76, which nearly matched levels seen in April 2020, during the height of COVID-19 concerns for farmers. This month’s survey was conducted from Sept. 9–13, 2024.

September’s survey revealed that farmers are increasingly worried about commodity prices, input costs, agricultural trade prospects and the potential impact of the upcoming election on their farm operations. When asked to identify their top concerns for the coming year, low commodity prices and high input costs were nearly tied, with 34% of farmers citing input prices and 33% pointing to lower output prices as their primary concerns. Interest rates trailed behind as a top concern for 17% of respondents.

Producers’ apprehensions about commodity prices matched up with their lack of confidence in the future of U.S. agricultural exports; only 26% of respondents expect exports to rise over the next five years, the most pessimistic response to this question since it was first introduced in 2019. Additionally, 78% of producers expressed concern that government policy changes following the fall 2024 elections could impact their farms.

“The continued drop in the barometer reflects deepening concerns among farmers regarding expectations for farm income in 2024 and 2025,” said James Mintert, the barometer’s principal investigator and director of Purdue University’s Center for Commercial Agriculture.

“It’s notable that producer sentiment dropped back to levels last seen in 2016 when the U.S. farm economy was in the early stages of an economic downturn. In addition to commodity prices and input costs weighing heavily on their operations, producers are also facing considerable uncertainty about what lies ahead for their farms with the possible government policy changes following the upcoming 2024 elections.”

The Farm Financial Performance Index fell for the third consecutive month, dropping to 68 in September from 72 in August. Farmers’ financial expectations have declined markedly compared to a year ago, as the index was at 86 in September 2023—an 18-point difference. While the Farm Capital Investment Index increased by 4 points from August to a reading of 35, it sits just above its all-time low, indicating that many producers believe it is not an opportune time for making large investments.

The Short-Term Farmland Value Expectations Index dropped by 10 points to 95. This is the first time since 2020 that the index fell below 100, indicating that more farmers are expecting a decline in farmland values over the next year than those who anticipate an increase. This month’s shift from a positive to a weaker outlook is attributable to a significant decrease in the percentage of producers forecasting rising values and a rise in those who expect values to remain steady.

The September survey marks the fourth consecutive year that the barometer has included questions regarding cover crop usage among corn and soybean producers. Consistent with prior years’ surveys, more than half of the respondents indicated that they currently plant cover crops on part of their farms, while an additional 1 in 5 farmers reported planting cover crops sometime in the past.

Interestingly, farmers who currently use cover crops say they are devoting a larger proportion of their farm’s acreage to cover crops than in the past. In 2021, 41% of cover crop users noted planting them on more than 25% of their farm’s acreage. This figure rose to 50% in 2023, and in this year’s survey, 68% of cover crop users indicated planting cover crops on more than one-fourth of their farms.