The core of this investigative effort is a convolutional neural network (CNN) model designed to classify the emotional valence of cultural heritage images into a simplified binary framework—positive or negative sentiment. By leveraging the Inception v3 architecture, renowned for its multi-branch convolutional design and superior image recognition capabilities, the researchers implemented a transfer learning strategy. This approach involved fine-tuning pre-trained models on curated datasets specifically aligned with cultural heritage themes, thus maximizing efficiency while minimizing the challenges associated with limited training data.

The training dataset used for the emotion classification model, known as DeepSent, is a product of meticulous annotation and consensus validation. Originating from social media platforms like Flickr and Twitter, this dataset initially encompassed a broad spectrum of daily life and natural imagery. Recognizing the stylistic and emotional divergence from cultural heritage images, the research team conducted rigorous screening to distill a high-confidence subset of 1,028 images exhibiting strong inter-rater agreement, ensuring robust model training and reliable sentiment classification.

Upon training, the model demonstrated impressive performance metrics with an 83.8% accuracy and an F1-score of 88.9%, affirming its capability to discern emotional emotions in visual content. However, to ensure applicability within the specific context of cultural heritage, the team undertook extensive validation using a curated selection of 100 images sourced from Redbook (Xiaohongshu) and Instagram. This step involved multilayered filtering and manual annotation, juxtaposing human judgments with model predictions, yielding a solid 74.3% accuracy and a notable 90.2% recall, thereby confirming the model’s sensitivity to negative emotional cues pertinent to heritage discourse.

The Heritage Sentiment Index itself is derived as the proportion of images classified by the model as carrying negative sentiment relative to the total number of cultural heritage images posted each day. By converting raw model outputs into this daily summary statistic, the HSI encapsulates public exposure to negatively valenced heritage imagery on a temporal scale. This index forms the foundation for exploring how visual emotional signals influence public engagement, behavioral intentions, and sentiment expressed in comments within social media ecosystems.

Beyond the binary classification scheme, the researchers also explored a probabilistic variant of the HSI, accounting for the model’s predicted confidence in negative sentiment identification. This alternative, which aggregates the weighted probabilities of negative sentiment across images, reinforces the robustness of the initial metric, as regression analyses reveal persistent predictive power of both versions on a suite of public behavioral outcomes, ranging from tourism intentions to interaction metrics like shares and likes.

Recognizing that sentiment classification thresholds may affect results, the study further tested an asymmetric dual-threshold strategy. Images with ambiguous prediction probabilities were omitted to refine signal clarity. Despite these variations, the HSI consistently demonstrated significant associations with behavioral responses, underscoring its resilience to classification nuances and confirming its validity as an emotion-driven indicator within cultural heritage communication.

In parallel complementing the image emotion recognition, the study introduced the Comment Sentiment Index (CSI), a textual sentiment measure computed through advanced natural language processing techniques. Utilizing Recursive Neural Tensor Networks (RNTN), the researchers extracted pessimism scores from user comments, effectively quantifying emotional tone at the sentence level. This multimodal approach allows for integrated analyses that compare the influence of both visual and textual emotional cues on public sentiment and behavior.

A key revelation from comparing the HSI and CSI across longitudinal datasets is their modest yet statistically significant positive correlation. This suggests that while visual and textual sentiment signals partially converge, they also operate through distinct cognitive and communicative pathways. Images wield strong symbolic and evocative power eliciting immediate emotional responses, whereas textual comments often reflect reflective or moderated sentiments, providing complementary dimensions to cultural heritage narratives online.

Data underpinning these insights were gathered through meticulous multi-stage sampling from primary social media platforms Redbook and Instagram between 2021 and 2025. The dataset encompasses over 14,000 culturally relevant images, carefully vetted to exclude advertisements, irrelevant content, or sensitive cultural imagery. This comprehensive compilation spans key global heritage events, cross-cultural contexts, and temporal fluctuations, delivering a rich foundation to explore how public emotion is mediated through visual culture over time.

Temporal analyses of HSI and CSI reveal dynamic patterns responding to significant heritage moments. For example, images documenting the repatriation of Benin Bronzes in 2021 triggered elevated negative sentiments reflecting solemnity and cultural justice. Similarly, devastating damage to Ukrainian heritage sites during armed conflict caused sharp declines in both visual and textual sentiment indices, illustrating how external shocks profoundly affect collective emotional landscapes. Positive surges in sentiment coincided with restorative milestones such as Notre-Dame Cathedral’s reconstruction and UNESCO heritage listings, demonstrating the index’s sensitivity to cultural pride and renewal narratives.

Intriguingly, immediate behavioral responses to increases in negative visual sentiment often manifested as suppression effects—reduced touring intentions, sharing, and comment positivity on the following day—suggesting aversion or caution in engaging with negatively charged heritage content. However, these trends reversed in subsequent days, indicating potential rebound effects characterized by increased attention and interaction. These findings reveal a complex, time-dependent interplay between emotional exposure and public behavioral dynamics in heritage communication.

Such nuanced understanding heralds practical implications for cultural heritage professionals and digital communicators. The Heritage Sentiment Index offers a quantitatively grounded tool to monitor emotional climates surrounding heritage imagery in real-time, potentially guiding strategies for content curation, community engagement, and public relations. By identifying emotional troughs and peaks, institutions can tailor messaging to optimize positive engagement or address emerging controversies with sensitivity.

Moreover, this research advances methodological frontiers by integrating deep learning-based visual sentiment analysis with semantic-rich textual sentiment modeling. This multidisciplinary fusion addresses longstanding challenges in capturing the full emotional spectrum of digital cultural expression, especially in short and context-dependent social media texts where traditional lexicon-based methods fall short. The adoption of RNTN for textual sentiment, aligned with CNN-driven visual sentiment detection, sets a new benchmark in multimodal sentiment analytics.

Ethical considerations underpin the research design, emphasizing respect for cultural diversity, privacy, and transparency. The dataset exclusively comprises publicly available images free of copyright restrictions, while sensitive content involving religious or political symbolism was conscientiously excluded. The aggregate-level focus circumvents individual tracking to protect user anonymity, aligning with international standards like the Declaration of Helsinki.

Further validation efforts, including robustness checks with different sentiment threshold settings and unwinsorized data analysis, affirm the reliability and stability of the HSI as an empirical tool. These steps reinforce confidence in the index’s predictive capacity across diverse cultural heritage contexts, underscoring its potential utility in broader heritage science and digital humanities research.

The study’s temporal scope—from post-pandemic cultural revitalization phases to major heritage conferences and policy changes—offers valuable longitudinal insights into how visual emotional cues modulate public sentiment and behavior amidst evolving socio-cultural landscapes. This comprehensive dataset presents unique opportunities for future research investigating causal mechanisms, cultural differences, and content effectiveness in heritage communication strategies.

In summary, this pioneering investigation elucidates the intricate role of visual emotional cues embedded in cultural heritage images in shaping public sentiment and behavioral intentions. The development and application of the Heritage Sentiment Index, supported by advanced computational models, provide a transformative approach to decoding and leveraging emotional signals in digital heritage contexts. This work not only enriches academic discourse but also offers practical pathways for cultivating more engaging, respectful, and emotionally resonant cultural heritage experiences online.

Subject of Research:
Analysis of emotional cues in cultural heritage images using machine learning to quantify public sentiment and predict behavioral intentions.

Article Title:
The impact of visual emotional cues in cultural heritage on public sentiment and behavioral intention: an image emotion recognition approach.

Article References:
Lai, S., Tian, Y. & Zhang, Q. The impact of visual emotional cues in cultural heritage on public sentiment and behavioral intention: an image emotion recognition approach. npj Herit. Sci. 14, 85 (2026). https://doi.org/10.1038/s40494-026-02348-3

Image Credits: AI Generated

DOI:
https://doi.org/10.1038/s40494-026-02348-3

In a groundbreaking study, researchers combined machine learning with traditional archival analysis and fieldwork to examine the chromatic evolution of over 3,000 heritage buildings in Singapore, spanning four decades before and after these sites were designated for conservation. This multifaceted methodological approach leveraged computational image analysis to decode subtle changes in dominant hues, color complexity, harmony, and saturation levels, while traditional text-based sources provided contextual depth to the meanings embedded within these chromatic shifts. The comprehensive dataset offers an unprecedented window into how urban color both responds to and reflects the multifarious cultural currents coursing through a cosmopolitan society.

The prevailing paradigm in heritage color conservation has typically regarded color as a fixed attribute—a pigment locked in time, emblematic of a particular era or ethnic identity. Yet, this research compellingly demonstrates that color in continuously inhabited heritage sites is anything but static. Instead, it is a living, evolving language, constantly reinterpreted through processes the authors term historicization, ethnicization, and commercialization. These processes signify how past narratives are invoked, ethnic identities asserted, and economic imperatives enacted, each layering distinct cultural meanings onto the visual fabric of built heritage.

Historicization manifests as deliberate efforts to evoke and preserve the ‘authentic’ feel of a locale, often through restoration to reference periods deemed culturally significant. Yet, the study reveals that even these efforts can incorporate contemporary reinterpretations of history, blending old and new shades to align heritage color with modern identities. This fluid interplay complicates the traditional notion of an unchanging local palette and highlights the dynamic way in which color acts as a bridge between past and present urban experiences.

Ethnicization refers to the ways in which color palettes come to symbolize, reinforce, or resist the identities of the diverse communities inhabiting these urban spaces. Singapore’s highly heterogeneous population—including Chinese, Malay, Indian, and migrant groups—imbues local color with layered meanings that adapt as demographics and cultural interactions evolve. Buildings within the same conservation zone might display chromatic variations reflecting this ethnic mosaic, reinforcing color as a potent marker of cultural expression and negotiation.

Commercialization adds another dimension to color evolution by introducing economic motivations into the heritage color equation. As neighborhoods undergo commercialization through tourism, retail, and real estate developments, color schemes are strategically adapted to appeal to broader audiences or market demands. This dynamic introduces tension between preserving cultural authenticity and embracing economic viability, ultimately reshaping local color in ways that reflect contemporary urban priorities.

The researchers’ application of a five-dimensional color analysis framework—examining dominant colors, complexity, harmony, saturation, and value—enabled a precise quantification of how heritage colors are transformed over time. For instance, an increase in color complexity and saturation might signify layers of new cultural influences or intensified commercial branding, whereas shifts in harmony could suggest negotiated continuities between tradition and innovation. These nuanced metrics, derived from computational techniques, provide a replicable and objective toolset to deepen our understanding of urban color dynamics.

What distinguishes this study is its insistence on viewing color as an integral component of sociocultural ecology rather than a mere physical attribute of architectural artifacts. This conceptual shift acknowledges that color is deeply embedded in the lived experiences, identities, and economic practices of urban inhabitants. The vibrancy or subtlety of a building’s hue thus becomes a form of ongoing dialogue—a constantly renegotiated semiotic resource that both shapes and is shaped by the changing urban milieu.

The implications for heritage conservation strategies are profound. Rather than attempting to arrest and freeze color in a presumed “original” form, conservationists are urged to embrace the fluidity and pluralistic nature of local color, recognizing it as an evolving phenomenon enriched by ongoing social interactions and cultural negotiations. This approach calls for adaptable conservation frameworks that can engage with contemporary community identities while honoring historical continuities.

Moreover, integrating computational machine learning with qualitative archival and field methods points toward a new interdisciplinary frontier in heritage studies. The capacity to analyze large-scale datasets involving visual and textual information offers unprecedented depth and precision, enabling researchers and practitioners to capture both measurable patterns and contextual narratives of color change. Such methods democratize access to conservation knowledge by transforming subjective visual impressions into actionable analytical insights.

Singapore, as a microcosm of global urban transformation, exemplifies how rapid cultural diversification and cosmopolitanism complicate traditional heritage paradigms. Its 40-plus years of conservation efforts demonstrate that color is neither monolithic nor immutable but rather a dynamic palimpsest reflecting layers of memory, identity, and economic activity. This finding resonates universally, calling on heritage management worldwide to rethink how color conservation aligns with realities of urban migration, globalization, and cultural hybridity.

As cities continue to evolve, urban planners, conservationists, and policymakers must reimagine color not as an ancillary aspect of built heritage but as a vital and evolving cultural form. The challenge lies in balancing the preservation of place-based meanings with the acceptance of inevitable change driven by demographic and socioeconomic forces. Doing so demands inclusive dialogues that position communities as active agents articulating the chromatic vocabularies of their surroundings.

Finally, this research underscores the vital role that interdisciplinary collaboration—melding art history, architecture, computational science, anthropology, and urban studies—plays in enriching our comprehension of urban color. By transcending disciplinary silos, scholars and practitioners can holistically address the intricate processes by which color becomes a mutable yet meaningful feature of cityscapes, simultaneously embodying history and signaling future trajectories.

In essence, sustaining the local color of a global city demands a nuanced appreciation of color as a fluid sociocultural phenomenon, continuously reshaped by historic memories, ethnic identities, and economic considerations. This study redefines urban color from a static preservation target to an evolving canvas that chronicles the multifaceted stories of its inhabitants, urging a transformation in heritage conservation that celebrates diversity, dynamism, and dialogue.

Subject of Research:

Article Title:

Article References:
Xue, X., Tian, Z., Yang, Y. et al. Sustaining the local color of a global city. Nat Cities 2, 400–412 (2025). https://doi.org/10.1038/s44284-025-00225-x

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s44284-025-00225-x