Tug-of-War of Emotion: Measuring and Modeling Sentiment Cycles in Chinese-Language Pop Song Lyrics, 1967-2023
Bibliographic record
Abstract
Scholars of popular music often assume that trends in the sentiment of pop song lyrics (becoming more positive or negative over time) “mirror” those in listeners’ preferences or the ethos of societies. For example, the detected monotone downward trend in the sentiment of English-language pop lyrics is typically interpreted as “reflecting” the deteriorating emotional and mental state in listener populations and/or the increasing demand for more negative (or less positive) lyric sentiment. This study challenges this “mirror interpretation” with an alternative “equilibration interpretation,” which posits that the average listener sentiment preference may remain largely stable across decades, and it is the equilibrating process that either brings the sentiment of pop lyrics closer to the listener preference or make the lyric sentiment oscillate around the listener preference. Exploring this alternative interpretation, this study measures and models the movement of lyric sentiment in more than 260,000 Chinese-language pop songs over six decades (1967–2023). To quantify the sentiment of a large volume of lyrics, a novel approach of combining large language model (LLM) and lexicon-based sentiment analysis is developed to extract affective information from lyrics. The resulting trajectory of measured average lyric sentiment exhibits a (damped) sine-wave-like pattern with an estimated period of 34 to 35 years. Moreover, this study does not stop at identifying sentiment patterns but goes further to build a math model that explains the possible cultural process—interactions between music listeners and lyricists—underlying the formation of such patterns. A parsimonious Damped Harmonic Oscillation (DHO) model can explicate both the periodic (in Chinese lyrics) and nonperiodic (in English lyrics) patterns of lyric sentiment movements, and the model parameters are estimated statistically. The explanatory power of the DHO model over empirical data lends support to the equilibration interpretation. In general, this study complicates any attempt to use changing features of mass cultural products as proxies for some underlying socio-psychological trends.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".