Background: Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony’s behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances in the colony. Therefore, one crucial step in analyzing bee colony sounds is to extract appropriate acoustic feature.Methods: This article uses VGGish (a visual geometry group—like audio classification model) embedding and Mel-frequency Cepstral Coefficient (MFCC) generated from three bee colony sound datasets, to train four machine learning algorithms to determine which acoustic feature performs better in bee colony sound recognition.Results: The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets.

Because the sounds emitted by a managed honeybee colony embrace a wealth of information about the status within and outside the beehive, researchers are interested in developing a beehive sound-based assessment of the colony situation. However, how the global experts rank this approach is unclear. We assessed the importance of beehive sound-based colony monitoring using formal expert elicitation. Our results indicate that policy-making bodies should focus on a non-invasive acoustic approach to monitor swarming, honeybee health, pesticides, and environmental pollution at apiaries, as these were considered very important factors with high confidence by global experts. Moreover, all other factors (pests and pathogens, weather conditions, predators, food availability, and spatiotemporal patterns) are rated as important, but experts’ confidence in acoustically monitoring a few of the factors differs. Because experienced forager bees emit bursting sounds during the waggle dance (particularly during the waggle-run phase) at a specific angle on a vertical comb within the hive, we propose an acoustics-based recording setup using a Raspberry Pi and a QuadMic Array to investigate how this sound can predict the spatial and temporal information of the available food sources. In this article, we highlight how the factors falling into the inconclusive category of confidence have the potential to be acoustically monitored. Besides, this paper suggests new and unexplored directions for opening a window for future research in beehive acoustics.

Honey bees play a crucial role in agricultural productivity and ecological stability, yet their interactions with environmental stressors, particularly volatile organic compounds (VOCs) and pollutants, pose significant challenges to their cognitive functions and behavior. This study investigates the effects of VOCs on the acoustic communication within honeybee colonies and foraging behavior, specifically focusing on how these compounds influence distance-related cues conveyed through colony sounds. Using OpenL3 embeddings and machine learning models, the study achieved accurate classification of food source distances based on acoustic features, with the K-Nearest Neighbors (KNN) model demonstrating superior performance. The introduction of ethyl acetate and acetone caused minor reductions in classification accuracy but had divergent impacts on foraging dynamics: ethyl acetate enhanced landing efficiency, whereas acetone disrupted foraging activity. These findings highlight the utility of acoustic analysis for studying honey bee behavior and underscore the importance of mitigating environmental stressors to sustain pollinator populations.