Harvesting Context and Mining Emotions Related to Olfactory Cultural Heritage

Massri, M.Besher; Novalija, Inna; Mladenić, Dunja; Brank, Janez; Silva, Sara Graça da; Marrouch, Natasza; Murteira, Carla; Hürriyetoğlu, Ali; Šircelj, Beno

doi:10.3390/mti6070057

Cited by 3 publications

(2 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For our immediate motivation and near-future application, this work follows Ref. [6] which combined emotion detection together with the detection of olfactory stimuli to begin associating certain emotions with sensory stimuli. The authors used only five emotions because their emotion detection model was trained on the Tales dataset [7].…”

Section: Motivationmentioning

confidence: 99%

Detecting Fine-Grained Emotions in Literature

Rei

Mladenić

2023

Applied Sciences

View full text Add to dashboard Cite

Emotion detection in text is a fundamental aspect of affective computing and is closely linked to natural language processing. Its applications span various domains, from interactive chatbots to marketing and customer service. This research specifically focuses on its significance in literature analysis and understanding. To facilitate this, we present a novel approach that involves creating a multi-label fine-grained emotion detection dataset, derived from literary sources. Our methodology employs a simple yet effective semi-supervised technique. We leverage textual entailment classification to perform emotion-specific weak-labeling, selecting examples with the highest and lowest scores from a large corpus. Utilizing these emotion-specific datasets, we train binary pseudo-labeling classifiers for each individual emotion. By applying this process to the selected examples, we construct a multi-label dataset. Using this dataset, we train models and evaluate their performance within a traditional supervised setting. Our model achieves an F1 score of 0.59 on our labeled gold set, showcasing its ability to effectively detect fine-grained emotions. Furthermore, we conduct evaluations of the model’s performance in zero- and few-shot transfer scenarios using benchmark datasets. Notably, our results indicate that the knowledge learned from our dataset exhibits transferability across diverse data domains, demonstrating its potential for broader applications beyond emotion detection in literature. Our contribution thus includes a multi-label fine-grained emotion detection dataset built from literature, the semi-supervised approach used to create it, as well as the models trained on it. This work provides a solid foundation for advancing emotion detection techniques and their utilization in various scenarios, especially within the cultural heritage analysis.

show abstract

Section: Motivationmentioning

confidence: 99%

Detecting Fine-Grained Emotions in Literature

Rei

Mladenić

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…[ 2 ] Common examples may be the perfume of a beloved one immediately activating past affective memories or an unpleasant smell of foods that had made us feel sick, automatically triggering an aversive sensation. [ 3 ] Industrial production and chemical plants are often the main sources of gaseous emissions. While these facilities may not pollute ambient air at concentrations higher than the limit for monitoring chemicals, they may produce mixtures of other compounds that cause odor pollution.…”

Section: Introductionmentioning

confidence: 99%

Artificial Olfactory Biohybrid System: An Evolving Sense of Smell

Qin

Wang

et al. 2022

Advanced Science

View full text Add to dashboard Cite

The olfactory system can detect and recognize tens of thousands of volatile organic compounds (VOCs) at low concentrations in complex environments. Bioelectronic nose (B-EN), which mimics olfactory systems, is becoming an emerging sensing technology for identifying VOCs with sensitivity and specificity. B-ENs integrate electronic sensors with bioreceptors and pattern recognition technologies to enable medical diagnosis, public security, environmental monitoring, and food safety. However, there is currently no commercially available B-EN on the market. Apart from the high selectivity and sensitivity necessary for volatile organic compound analysis, commercial B-ENs must overcome issues impacting sensor operation and other problems associated with odor localization. The emergence of nanotechnology has provided a novel research concept for addressing these problems. In this work, the structure and operational mechanisms of biomimetic olfactory systems are discussed, with an emphasis on the development and immobilization of materials. Various biosensor applications and current developments are reviewed. Challenges and opportunities for fulfilling the potential of artificial olfactory biohybrid systems in fundamental and practical research are investigated in greater depth.

show abstract

Could this be next for corpus linguistics? Methods of semi-automatic data annotation with contextualized word embeddings

Fonteyn,

Manjavacas,

Haket

et al. 2024

Linguistics Vanguard

View full text Add to dashboard Cite

This paper explores how linguistic data annotation can be made (semi-)automatic by means of machine learning. More specifically, we focus on the use of “contextualized word embeddings” (i.e. vectorized representations of the meaning of word tokens based on the sentential context in which they appear) extracted by large language models (LLMs). In three example case studies, we assess how the contextualized embeddings generated by LLMs can be combined with different machine learning approaches to serve as a flexible, adaptable semi-automated data annotation tool for corpus linguists. Subsequently, to evaluate which approach is most reliable across the different case studies, we use a Bayesian framework for model comparison, which estimates the probability that the performance of a given classification approach is stronger than that of an alternative approach. Our results indicate that combining contextualized word embeddings with metric fine-tuning yield highly accurate automatic annotations.

show abstract

Harvesting Context and Mining Emotions Related to Olfactory Cultural Heritage

Cited by 3 publications

References 84 publications

Detecting Fine-Grained Emotions in Literature

Detecting Fine-Grained Emotions in Literature

Artificial Olfactory Biohybrid System: An Evolving Sense of Smell

Could this be next for corpus linguistics? Methods of semi-automatic data annotation with contextualized word embeddings

Contact Info

Product

Resources

About