Predicting and explaining with machine learning models: Social science as a touchstone

Buchholz, Oliver; Grote, Thomas

doi:10.1016/j.shpsa.2023.10.004

Cited by 3 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It explores the implications of this shift for scientific explanation and the potential future directions of ML in scientific research. Finally, Buchholz et al [32] discuss some of the insights into the use of ML models as a method for science outside of traditional success areas. It opens up a debate on how ML coordinates with other scientific methods, transitioning from explanatory to predictive models, and how it applies in various scientific domains like AlphaFold in protein folding prediction.…”

Section: And Scientific Methodsmentioning

confidence: 99%

The Challenges of Machine Learning: A Critical Review

Barbierato,

Gatti

2024

Electronics

View full text Add to dashboard Cite

The concept of learning has multiple interpretations, ranging from acquiring knowledge or skills to constructing meaning and social development. Machine Learning (ML) is considered a branch of Artificial Intelligence (AI) and develops algorithms that can learn from data and generalize their judgment to new observations by exploiting primarily statistical methods. The new millennium has seen the proliferation of Artificial Neural Networks (ANNs), a formalism able to reach extraordinary achievements in complex problems such as computer vision and natural language recognition. In particular, designers claim that this formalism has a strong resemblance to the way the biological neurons operate. This work argues that although ML has a mathematical/statistical foundation, it cannot be strictly regarded as a science, at least from a methodological perspective. The main reason is that ML algorithms have notable prediction power although they cannot necessarily provide a causal explanation about the achieved predictions. For example, an ANN could be trained on a large dataset of consumer financial information to predict creditworthiness. The model takes into account various factors like income, credit history, debt, spending patterns, and more. It then outputs a credit score or a decision on credit approval. However, the complex and multi-layered nature of the neural network makes it almost impossible to understand which specific factors or combinations of factors the model is using to arrive at its decision. This lack of transparency can be problematic, especially if the model denies credit and the applicant wants to know the specific reasons for the denial. The model’s “black box” nature means it cannot provide a clear explanation or breakdown of how it weighed the various factors in its decision-making process. Secondly, this work rejects the belief that a machine can simply learn from data, either in supervised or unsupervised mode, just by applying statistical methods. The process of learning is much more complex, as it requires the full comprehension of a learned ability or skill. In this sense, further ML advancements, such as reinforcement learning and imitation learning denote encouraging similarities to similar cognitive skills used in human learning.

show abstract

Section: And Scientific Methodsmentioning

confidence: 99%

The Challenges of Machine Learning: A Critical Review

Barbierato,

Gatti

2024

Electronics

View full text Add to dashboard Cite

show abstract

What do you do or with whom? Understanding happiness with the tourism experience: an AI approach applied to Instagram

Blanco-Moreno,

González-Fernández,

Muñoz-Gallego

et al. 2024

Humanit Soc Sci Commun

View full text Add to dashboard Cite

More and more tourists are sharing their experiences on their social media through a combination of photos, texts, and hashtags. But there is a scarcity of studies in literature on analyzing tourists’ visual content in relation to tourism destinations. To address this gap in literature, this study explores how and with whom users express the greatest happiness in holiday destinations, and how they share it with their community, through a mixed methods approach composed of analysis of images, text, and metadata. This approach allows us to address the objective of this research, which is the prediction of the happiness felt by tourists during their experience, using innovative techniques that allow the independent variables to be obtained. To predict tourist satisfaction, two sources of data, photos and texts, are analyzed: a novel approach and little explored in the literature, but necessary due to the interaction of both variables. This study applies various artificial intelligence analyses on visual content (deep learning), and textual and metadata content (machine learning) to 39,235 Instagram posts shared by tourists since the emergence of Instagram thirteen years ago, at a cultural and gastronomic tourist destination. The findings of the visual content analysis showed that socialization and company, that is, traveling and interacting with people, was a key aspect of a positive tourism experience. In addition, the gender of the people with whom they traveled, and the tourist’s narcissism were also key aspects in the generation and expression of positive emotions. Regarding the analysis of the textual content, the results showed that when tourists enjoyed a positive experience, they became more involved in the generation of content, that is, they showed their happiness through positive words.

show abstract

Applications of Artificial Intelligence in Contemporary Sociology

Jiménez Pérez,

Hernández de la Cruz

2024

LatIA

View full text Add to dashboard Cite

Predicting and explaining with machine learning models: Social science as a touchstone

Cited by 3 publications

References 51 publications

The Challenges of Machine Learning: A Critical Review

The Challenges of Machine Learning: A Critical Review

What do you do or with whom? Understanding happiness with the tourism experience: an AI approach applied to Instagram

Applications of Artificial Intelligence in Contemporary Sociology

Contact Info

Product

Resources

About