The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales

Spoken language, whether produced by humans or large language models (LLM), unfolds over time with varying semantic content. However, we still lack simple, interpretable time-series features that capture how generic versus specific content is distributed over time, and that can be used to compare human and AI-generated speech. We introduce a semantic-timescale analysis pipeline that turns word-level transcripts with timestamps into semantic time-series. For each spoken narrative, we compute (i) semantic specificity using WordNet-based word depth and (ii) contextual similarity using SBERT embeddings and quantify their temporal dependence using autocorrelation-window measures (ACW-0 and related metrics). We then compare original speech to multiple shuffled controls that selectively disrupt lexical identity, temporal order, and word duration. Across human-read autobiographical narratives, TTS readings, and LLM-generated texts rendered with TTS, we find that segments with longer ACW-0 in the semantic time-series tend to contain more generic vocabulary, whereas segments with shorter ACW-0 are enriched in more specific words. These associations are strongly attenuated or abolished when word order and timing are randomized, indicating that ACW-based measures capture non-trivial temporal organization of semantic content beyond static lexical distributions. Our results suggest that ACW-based semantic timescales are a useful family of features for analyzing and comparing the temporal structure of human and AI-generated speech.

Local reservoir model for choice-based learning

Decision making based on behavioral and neural observations of living systems has been extensively studied in brain science, psychology, and other disciplines. Decision-making mechanisms have also been experimentally implemented in physical processes, such as single photons and chaotic lasers. The findings of these experiments suggest that there is a certain common basis in describing decision making, regardless of its physical realizations. In this study, we propose a local reservoir model to account for choice-based learning (CBL). CBL describes decision consistency as a phenomenon where making a certain decision increases the possibility of making that same decision again later, which has been intensively investigated in neuroscience, psychology, etc. Our proposed model is inspired by the viewpoint that a decision is affected by its local environment, which is referred to as a local reservoir. If the size of the local reservoir is large enough, consecutive decision making will not be affected by previous decisions, thus showing lower degrees of decision consistency in CBL. In contrast, if the size of the local reservoir decreases, a biased distribution occurs within it, which leads to higher degrees of decision consistency in CBL. In this study, an analytical approach on local reservoirs is presented, as well as several numerical demonstrations. Furthermore, a physical architecture for CBL based on single photons is discussed, and the effects of local reservoirs is numerically demonstrated. Decision consistency in human decision-making tasks and in recruiting empirical data are evaluated based on local reservoir. In summary, the proposed local reservoir model paves a path toward establishing a foundation for computational mechanisms and the systematic analysis of decision making on different levels.