Stunting remains a particular challenge in Sub-Saharan Africa. Despite encouraging declines in Tanzania over the past 25 years, one-third of Tanzanian children under the age of five years are stunted. Diarrhea remains...Stunting remains a particular challenge in Sub-Saharan Africa. Despite encouraging declines in Tanzania over the past 25 years, one-third of Tanzanian children under the age of five years are stunted. Diarrhea remains one of the greatest causes of childhood stunting worldwide. Mass media has been used to improve the uptake of behaviors associated with reductions in diarrhea. This study evaluates the effectiveness of a mass media campaign in the Lake Zone region of Tanzania from 2015-2020 and positive changes in caregiver health-seeking behaviors related to diarrhea in children. Approximately 5000 households participated in a cross-sectional survey after a communications campaign. Exposure variables included hearing and seeing radio and TV spots and participating in a variety of interpersonal communication approaches. Study results indicated primary caregivers (mothers) exposed to media messages only (OR 1.66, CI 1.05 - 2.62), and to media messages and interpersonal communication (OR 2.51, CI 1.48 - 4.26), were more likely to seek advice or treatment for diarrhea from a health facility. Primary caregivers exposed to both media messages and interpersonal communication were more likely to give oral rehydration salts (OR 2.56, CI 1.72 - 3.79), zinc tablets/syrup (OR 1.74, CI 1.18 - 2.57), and homemade fluids (OR 2.02, CI 1.15 - 3.55) when their children had diarrhea. Male heads of household (fathers) exposure to mass media was not associated with care-seeking for diarrhea treatment.展开更多
The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in S...The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.展开更多
Floods are among the most frequent and devastating natural hazards and disasters in many southern states in the United States.This study examined the relationship and reciprocal predictability between two theoretical ...Floods are among the most frequent and devastating natural hazards and disasters in many southern states in the United States.This study examined the relationship and reciprocal predictability between two theoretical constructs-risk perception attitude(RPA)and informationseeking efficacy(ISE)——in regard to pluvial floods.In addition,this study extended these theoretical constructs to investigate differences in RPA and ISE among potential audience segments,providing practitioners with applicable insights for designing effective flood prevention and risk management campaigns.Analysis of data from 716 residents in south Louisiana revealed a statistically strong relationship between RPA and ISE.This research also identified specific audience segments that would benefit from an increase in RPA and ISE concerning floods.These meaningful findings infonn a discussion of the theoretical and practical implications of the relationship between RPA and ISE and guide future disaster preparation campaigns and policies.展开更多
文摘Stunting remains a particular challenge in Sub-Saharan Africa. Despite encouraging declines in Tanzania over the past 25 years, one-third of Tanzanian children under the age of five years are stunted. Diarrhea remains one of the greatest causes of childhood stunting worldwide. Mass media has been used to improve the uptake of behaviors associated with reductions in diarrhea. This study evaluates the effectiveness of a mass media campaign in the Lake Zone region of Tanzania from 2015-2020 and positive changes in caregiver health-seeking behaviors related to diarrhea in children. Approximately 5000 households participated in a cross-sectional survey after a communications campaign. Exposure variables included hearing and seeing radio and TV spots and participating in a variety of interpersonal communication approaches. Study results indicated primary caregivers (mothers) exposed to media messages only (OR 1.66, CI 1.05 - 2.62), and to media messages and interpersonal communication (OR 2.51, CI 1.48 - 4.26), were more likely to seek advice or treatment for diarrhea from a health facility. Primary caregivers exposed to both media messages and interpersonal communication were more likely to give oral rehydration salts (OR 2.56, CI 1.72 - 3.79), zinc tablets/syrup (OR 1.74, CI 1.18 - 2.57), and homemade fluids (OR 2.02, CI 1.15 - 3.55) when their children had diarrhea. Male heads of household (fathers) exposure to mass media was not associated with care-seeking for diarrhea treatment.
基金the research project LaTe4PoliticES(PID2022-138099OB-I00)funded by MCIN/AEI/10.13039/501100011033 and the European Fund for Regional Development(ERDF)-a way to make Europe.Tomás Bernal-Beltrán is supported by University of Murcia through the predoctoral programme.
文摘The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.
文摘Floods are among the most frequent and devastating natural hazards and disasters in many southern states in the United States.This study examined the relationship and reciprocal predictability between two theoretical constructs-risk perception attitude(RPA)and informationseeking efficacy(ISE)——in regard to pluvial floods.In addition,this study extended these theoretical constructs to investigate differences in RPA and ISE among potential audience segments,providing practitioners with applicable insights for designing effective flood prevention and risk management campaigns.Analysis of data from 716 residents in south Louisiana revealed a statistically strong relationship between RPA and ISE.This research also identified specific audience segments that would benefit from an increase in RPA and ISE concerning floods.These meaningful findings infonn a discussion of the theoretical and practical implications of the relationship between RPA and ISE and guide future disaster preparation campaigns and policies.
