Using social media for political discourse has received much attention due to its real-time and interactive nature, especially around election time. Recent studies have explored the power of a single social media platform, such as Google or twitter, on recording current social trends and predicting the voting outcomes in a particular region. These pilot studies, though being very interesting, fail to integrate more of the heterogeneous information available online, nor do they consider the demographical bias of online users most of whom are young people. In this work, by aggregating online data from social media and offline data from pollsters, we achieve accurate prediction of candidates' votes in 2016 Taiwan presidential election, with error rates ranging from 0.30% to 2.85%. Our main contributions are summarized as follows. First, to our best knowledge, we are among the earliest studies to fuse heterogeneous information for election prediction. Three types of online information as signals of online public opinion are obtained from social networking sites (e.g. Facebook and Twitter), search engines (e.g. Google), and campaign homepages. To avoid voter bias, we further introduce offline demographical information to weight online and offline voting for a final prediction. Second, by taking election prediction as an unsupervised sequential prediction task, we introduce Kalman filter, a widely used signal processing method, to automatically select reliable information sources and fuse them for daily prediction. Finally, by taking into account the sensitivity of tweet volumes on Twitter, the Moving Average model is applied for real-time burst detection. Our work provides unique values to identifying important online information sources as well as their valid periods for election prediction, and shows great potentials for event influence analytics.

To compare the impact of different post-harvest handling methods on volatile and non-volatile compounds, a total of 54 live large yellow croakers were subjected to commercial slaughter (CS), spinal cord cutting (SCC), or spinal cord cutting and bleeding (SCCB). The fish samples were ice-stored for 72 h, followed by the analysis of volatile compounds using gas chromatography–ion mobility spectrometry and non-volatile compounds using LC-MS-based untargeted metabolomics. The results revealed the detection of a total of 28 volatile organic compounds, with 23 being successfully identified, predominantly including alcohols, aldehydes, esters, ketones, and heterocyclic compounds. Substances such as (E)-2-nonenal and 2-butanone are highly sensitive to post-harvest handling methods during ice storage. Furthermore, 943 non-volatile metabolites were identified, showing significant differences in 180, 100, 117, and 186 metabolites across comparisons of SCC 0 h/CS 0 h, SCCB 0 h/CS 0 h, SCC 72 h/CS 72 h, and SCCB 72 h/CS 72 h, respectively. Notably, the altered metabolic pathways mainly involved fatty acid and amino acid metabolism, including pathways like glycerophospholipid metabolism and arginine biosynthesis. This study revealed the potential mechanisms underlying the enhancement of fish quality through spinal cord cutting and bleeding.

The large yellow croaker (Larimichthys crocea) is susceptible to microbial contamination during storage due to its high protein and moisture contents. This study was designed to find a new way to reduce bacteria in large yellow croakers by combining slightly acidic electrolyzed water (SAEW) with nano-bubble (NB) technology. Exploring the effects of available chlorine concentration (ACC), processing time, and water temperature on the bacteria reduction effect of the SAEW-NB treatment for large yellow croakers. Also, the effects of the SAEW-NB combined treatment on sensory evaluation, total viable counts (TVCs), total volatile basic nitrogen (TVB-N), texture, taste profile, and volatile flavor compounds of large yellow croakers were analyzed during the storage period at 4 °C. The results show that the SAEW-NB treatment achieved significantly enhanced microbial reduction compared to individual treatments. Under the conditions of a 4 °C water temperature, 40 mg/L ACC, and 15 min treatment, the SAEW-NB treatment inhibited the increases in physical and chemical indexes such as TVC and TVB-N, maintained the fish texture, and delayed the production of off-flavor volatiles such as aldehydes, alcohols, esters, and ketones, compared with the control group (CG) during storage at 4 °C. In conclusion, the SAEW-NB treatment could better retard fish spoilage, extending the shelf life by approximately 2 days. It might be a promising new industrial approach for large yellow croakers’ storage.

As a representative of traditional Chinese fermented fish, fermented large yellow croaker (Larimichthys crocea) is characterized by its rich aroma, appealing color, distinctive flavor, and long shelf life. In this study, Saccharomyces cerevisiae (S. cerevisiae) and Levilactobacillus brevis (L. brevis) were inoculated to enhance fermentation, and their effects on biogenic amine (BA) formation, volatile flavor compounds (VFCs), and microbial community composition were investigated. Combined inoculation significantly reduced most BAs and nitrite levels, thereby improving the safety of fermented large yellow croaker. The S. cerevisiae-inoculated group exhibited higher contents of ester compounds such as 3-methylbutyl acetate, 2-methylpropyl acetate, and ethyl 2-methylbutanoate. L. brevis effectively suppressed spoilage and amine-producing bacteria, including Aeromonas, Shewanella, and Morganella. Pearson’s correlation analysis revealed that Levilactobacillus was positively correlated with butyl 2-methylbutanoate, (Z)-4-heptenal, pentyl acetate, 2-ethyl-3-methylpyrazine, 3-methylbutyl acetate, 4-methyl-2-pentanone, 3-pentanone, and propanal, while Saccharomyces showed positive correlations with propionaldehyde, 1-penten-3-ol, 4-methyl-3-penten-2-one, (E)-2-pentenal, and 2-hexenal. In contrast, BAs were negatively correlated with Levilactobacillus and Saccharomycopsis, but positively correlated with Aeromonas, Shewanella, Photobacterium, Vagococcus, Vibrio, Morganella, Lactococcus, Apiotrichum, and Cutaneotrichosporon. Overall, these findings demonstrate that L. brevis and S. cerevisiae improve both the flavor and safety of fermented large yellow croaker. This study offers a theoretical basis for advancing industrial production of fermented fish products.

The large yellow croaker (Larimichthys crocea) is an economically significant aquaculture species in Asia, with skin coloration being a key quality attribute affecting consumer choice and commercial value. This study integrated morphological, biochemical, and proteomic approaches to investigate chromatophore characteristics, pigment composition, and diurnal body color variation in the large yellow croaker. Colorimetric analysis showed the highest yellowness, redness, and lightness values in ventral skin, followed by caudal skin, with dorsal skin showing the least yellowness. Three major chromatophores were identified: melanophores, xanthophores, and iridophores. Xanthophores were abundant in ventral and caudal skin, showing larger size and deeper pigmentation ventrally, while melanophores dominated dorsally and iridophores were mainly on scales. Skin and fins were key sites for carotenoid deposition, with lutein as the predominant carotenoid. Esters of lutein and zeaxanthin were the main contributors to yellow coloration in fish. A strong positive correlation was found between skin yellowness and total carotenoid content (R = 0.91, p < 0.05). The aggregation and dispersion of xanthosomes within xanthophores appeared to be the key driver behind the light-influenced diurnal body color variation. Proteomic analysis revealed motor proteins (such as KIF21, DYNC1L1, and MYO9) and pathways related to intracellular granule movement were probably related to the pigment transport in chromatophores of large yellow croaker. In addition, tubulin dynamics also appeared to participate in pigment translocation. This study is helpful to understand the pigmentary basis of this important farmed sea fish and provides a foundation for improving the golden color traits and further molecular research on diurnal color changes in large yellow croaker.

Large yellow croaker (Larimichthys crocea) is an economically important marine fish, yet rapid and non-destructive discrimination between sea-caught and farmed collection-source groups remains challenging. This study developed a fish-level analytical workflow integrating YOLO11n-seg instance segmentation with visible–near-infrared hyperspectral imaging to extract relative reflectance ratios from six anatomical regions. The analytical cohort comprised 258 unique fish, including 171 sea-caught and 87 farmed individuals. Source categories were assigned according to the original capture or cage-culture collection channels. Fish identity was used as the grouping unit in five-fold internal cross-validation, and classification performance was evaluated based on out-of-fold fish-level predictions. Logistic-regression models achieved AUC values ranging from 0.985 to 1.000 across the six individual anatomical regions. The combined six-region model achieved an accuracy of 0.996 (95% CI, 0.988–1.000) and an AUC of 1.000 (95% CI, 1.000–1.000) within the present cohort. For anatomical-region segmentation, the 20-image validation set contained 140 annotated instances. Bounding-box precision, recall, mAP@0.5, and mAP@0.5–0.95 were 0.976, 0.983, 0.981, and 0.700, respectively, while the corresponding mask metrics were 0.969, 0.976, 0.972, and 0.669. These results indicate that region-specific hyperspectral information can support highly accurate internal discrimination between the two collection-source groups and provide an interpretable basis for characterizing source-associated spectral differences. However, the source labels were not independently verified, potentially influential covariates were incompletely recorded, and no independent external cohort was available. Therefore, the present findings should be interpreted as internally validated collection-source discrimination rather than verified provenance authentication or evidence of external generalizability.