The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments

Text embeddings have become central to computational social science and psychology, enabling scalable measurement of meaning and mixed-method inference. Yet most representation learning is optimized and evaluated for prediction and retrieval, yielding a prediction-measurement gap: representations that perform well as features may be poorly suited as scientific instruments. The paper argues that scientific meaning analysis motivates a distinct family of objectives - scientific usability - emphasizing geometric legibility, interpretability and traceability to linguistic evidence, robustness to non-semantic confounds, and compatibility with regression-style inference over semantic directions. Grounded in cognitive and neuro-psychological views of meaning, the paper assesses static word embeddings and contextual transformer representations against these requirements: static spaces remain attractive for transparent measurement, whereas contextual spaces offer richer semantics but entangle meaning with other signals and exhibit geometric and interpretability issues that complicate inference. The paper then outlines a course-setting agenda around (i) geometry-first design for gradients and abstraction, including hierarchy-aware spaces constrained by psychologically privileged levels; (ii) invertible post-hoc transformations that recondition embedding geometry and reduce nuisance influence; and (iii) meaning atlases and measurement-oriented evaluation protocols for reliable and traceable semantic inference. As the field debates the limits of scale-first progress, measurement-ready representations offer a principled new frontier.

Bias-Free Sentiment Analysis through Semantic Blinding and Graph Neural Networks

This paper introduces the Semantic Propagation Graph Neural Network (SProp GNN), a machine learning sentiment analysis (SA) architecture that relies exclusively on syntactic structures and word-level emotional cues to predict emotions in text. By semantically blinding the model to information about specific words, it is robust to biases such as political or gender bias that have been plaguing previous machine learning-based SA systems. The SProp GNN shows performance superior to lexicon-based alternatives such as VADER and EmoAtlas on two different prediction tasks, and across two languages. Additionally, it approaches the accuracy of transformer-based models while significantly reducing bias in emotion prediction tasks. By offering improved explainability and reducing bias, the SProp GNN bridges the methodological gap between interpretable lexicon approaches and powerful, yet often opaque, deep learning models, offering a robust tool for fair and effective emotion analysis in understanding human behavior through text.

Bias Free Sentiment Analysis

This paper introduces the Semantic Propagation Graph Neural Network (SProp GNN), a machine learning sentiment analysis (SA) architecture that relies exclusively on syntactic structures and word-level emotional cues to predict emotions in text. By semantically blinding the model to information about specific words, it is robust to biases such as political or gender bias that have been plaguing previous machine learning-based SA systems. The SProp GNN shows performance superior to lexicon-based alternatives such as VADER and EmoAtlas on two different prediction tasks, and across two languages. Additionally, it approaches the accuracy of transformer-based models while significantly reducing bias in emotion prediction tasks. By offering improved explainability and reducing bias, the SProp GNN bridges the methodological gap between interpretable lexicon approaches and powerful, yet often opaque, deep learning models, offering a robust tool for fair and effective emotion analysis in understanding human behavior through text.

Uncovering Political Bias in Emotion Inference Models: Implications for sentiment analysis in social science research

This paper investigates the presence of political bias in emotion inference models used for sentiment analysis (SA) in social science research. Machine learning models often reflect biases in their training data, impacting the validity of their outcomes. While previous research has highlighted gender and race biases, our study focuses on political bias - an underexplored yet pervasive issue that can skew the interpretation of text data across a wide array of studies. We conducted a bias audit on a Polish sentiment analysis model developed in our lab. By analyzing valence predictions for names and sentences involving Polish politicians, we uncovered systematic differences influenced by political affiliations. Our findings indicate that annotations by human raters propagate political biases into the model's predictions. To mitigate this, we pruned the training dataset of texts mentioning these politicians and observed a reduction in bias, though not its complete elimination. Given the significant implications of political bias in SA, our study emphasizes caution in employing these models for social science research. We recommend a critical examination of SA results and propose using lexicon-based systems as a more ideologically neutral alternative. This paper underscores the necessity for ongoing scrutiny and methodological adjustments to ensure the reliability and impartiality of the use of machine learning in academic and applied contexts.

Predicting Emotion Intensity in Polish Political Texts: Comparing Supervised Models and Large Language Models in a Resource-Poor Language

This study explores the use of large language models (LLMs) to predict emotion intensity in Polish political texts, a resource-poor language context. The research compares the performance of several LLMs against a supervised model trained on an annotated corpus of 10,000 social media texts, evaluated for the intensity of emotions by expert judges. The findings indicate that while the supervised model generally outperforms LLMs, offering higher accuracy and lower variance, LLMs present a viable alternative, especially given the high costs associated with data annotation. The study highlights the potential of LLMs in low-resource language settings and underscores the need for further research on emotion intensity prediction and its application across different languages and continuous features. The implications suggest a nuanced decision-making process to choose the right approach to emotion prediction for researchers and practitioners based on resource availability and the specific requirements of their tasks.