Integrating Individual Factors to Construct Recognition Models of Consumer Fraud Victimization.

Consumer financial fraud has become a serious problem because it often causes victims to suffer economic, physical, mental, social, and legal harm. Identifying which individuals are more likely to be scammed may mitigate the threat posed by consumer financial fraud. Based on a two-stage conceptual framework, this study integrated various individual factors in a nationwide survey (36,202 participants) to construct fraud exposure recognition (FER) and fraud victimhood recognition (FVR) models by utilizing a machine learning method. The FER model performed well (f1 = 0.727), and model interpretation indicated that migration status, financial status, urbanicity, and age have good predictive effects on fraud exposure in the Chinese context, whereas the FVR model shows a low predictive effect (f1 = 0.565), reminding us to consider more psychological factors in future work. This research provides an important reference for the analysis of individual differences among people vulnerable to consumer fraud.

Quantifying the spatial pattern of urban heat islands and the associated cooling effect of blue-green landscapes using multisource remote sensing data.

Surface urban heat islands (SUHIs) are a global concern. Although their spatial pattern and the cooling effect of blue-green landscapes have been documented, exploring more accurate and quantitative results is still necessary. For Hangzhou, we combined nighttime light (NTL) data with LST images to investigate the spatial morphology of SUHIs and analyze the cooling effect of blue-green landscapes. The radiative transfer equation (RTE) method was used to derive the land surface temperature (LST). Then, based on the unique feature of Luojia1-01 NTL data, the concentric zone model (CZM) was proposed to depict the urban spatial structure. The CZM was applied to construct a number of equal-area concentric belts along the urban-rural gradient to determine the SUHI range and the corresponding blue-green landscape cooling effects. Finally, local Moran's I indices were adopted to identify the cold-hot spots of the SUHI and the relationship with land use. The minimum, average and maximum LSTs were 21.81 °C, 32.79 °C and 44.79 °C, respectively. Additionally, 59.16 % of the study area was affected by the SUHI, and the mean LST inside the SUHI was 36.4 °C, clearly higher than that of the rural area. The SUHI hotpots were clustered in regions with intensive human activities, forming archipelagos. Due to the different blue-green landscape densities, the cooling capacity had spatial heterogeneity in different urban rural belts (URBs), and the cooling capacity of URB16 was approximately 71 times that of URB1. The cooling efficiency increased with blue-green landscape density in general; hence, blue-green landscape density thresholds of 40 % and 70 % were recommended in the urban planning of different urban function zones. Relating the pattern of NTL data to LST images provide meaningful insight into the spatial pattern of SUHIs and the optimization of urban planning.

Human Personality Is Associated with Geographical Environment in Mainland China.

Recent psychological research shown that the places where we live are linked to our personality traits. Geographical aggregation of personalities has been observed in many individualistic nations; notably, the mountainousness is an essential component in understanding regional variances in personality. Could mountainousness therefore also explain the clustering of personality-types in collectivist countries like China? Using a nationwide survey (29,838 participants) in Mainland China, we investigated the relationship between the Big Five personality traits and mountainousness indicators at the provincial level. Multilevel modelling showed significant negative associations between the elevation coefficient of variation (Elevation CV) and the Big Five personality traits, whereas mean elevation (Elevation Mean) and the standard deviation in elevation (Elevation STD) were positively associated with human personalities. Subsequent machine learning analyses showed that, for example, Elevation Mean outperformed other mountainousness indicators regarding correlations with neuroticism, while Elevation CV performed best relative to openness models. Our results mirror some previous findings, such as the positive association between openness and Elevation STD, while also revealing cultural differences, such as the social desirability of people living in China's mountainous areas.

Using machine learning analysis to interpret the relationship between music emotion and lyric features.

Melody and lyrics, reflecting two unique human cognitive abilities, are usually combined in music to convey emotions. Although psychologists and computer scientists have made considerable progress in revealing the association between musical structure and the perceived emotions of music, the features of lyrics are relatively less discussed. Using linguistic inquiry and word count (LIWC) technology to extract lyric features in 2,372 Chinese songs, this study investigated the effects of LIWC-based lyric features on the perceived arousal and valence of music. First, correlation analysis shows that, for example, the perceived arousal of music was positively correlated with the total number of lyric words and the mean number of words per sentence and was negatively correlated with the proportion of words related to the past and insight. The perceived valence of music was negatively correlated with the proportion of negative emotion words. Second, we used audio and lyric features as inputs to construct music emotion recognition (MER) models. The performance of random forest regressions reveals that, for the recognition models of perceived valence, adding lyric features can significantly improve the prediction effect of the model using audio features only; for the recognition models of perceived arousal, lyric features are almost useless. Finally, by calculating the feature importance to interpret the MER models, we observed that the audio features played a decisive role in the recognition models of both perceived arousal and perceived valence. Unlike the uselessness of the lyric features in the arousal recognition model, several lyric features, such as the usage frequency of words related to sadness, positive emotions, and tentativeness, played important roles in the valence recognition model.