Utilization of marketing automation tools for delivery of a faculty development curriculum.

Background: Physician clinical educators play important roles in teaching, providing feedback, and evaluating trainees, but they often have variable preparation and competing demands on their time that make universal participation in workshops, seminars, or short courses designed to foster these skillsets inefficient or impossible. Methods: We designed and implemented a 52-week synchronous curriculum designed to address faculty opportunities to improve teaching skills, feedback for residents and medical students, and evaluation skills, which were delivered using marketing automation tools, including text messaging and email. We evaluated the programmatic impact and feasibility of using the implementation science framework. Results: Over a 104-week evaluation period, there were at least 10,499 total content impressions and 4558 unique recipients, indicating the significant reach of this program to approximately 120 faculty members. Faculty engagement with continuing education materials remained stable or increased over the 2-year evaluation period, indicating that programs like ours can have sustainable impacts. Resident evaluations of faculty across the six key domains also improved after the implementation of the program. Conclusions: Our experience with digital marketing tools reflects that they can be used to deliver impactful curricular content to faculty for continuing educational purposes and that faculty can use these resources in a sustainable way. However, because of the incomplete reach with any single communication, this type of content delivery is not appropriate for isolation as a material of critical importance. More research is needed to identify the best practices and additional education-related uses of this technology.

Provision of Telepsychological Care Via Email during COVID-19 Confinement: An Exploratory Study.

Within teletherapy, email interventions have been studied scarcely. For this reason, this exploratory study aims to characterize the assistance provided by email in a university telepsychology service and to compare the data with the assistance provided by telephone in the same service and period. For this purpose, the records of 81 users assisted via email during the COVID-19 pandemic lockdown in Spain were analyzed. The data were compared with those of the 338 users assisted by telephone in the same period. Despite its many limitations, results indicate high satisfaction with the email modality. Users express that they prefer a preference for using email when they do not feel safe in other ways. We found a lot of variation between the number of emails exchanged and the days that each case was active. Additionally, differences were found with telephone users in aspects such as age (email users being younger) and in a depression screening (email users scoring more positively). This study concludes on the high potential of this channel for the application of certain techniques (e.g., psychoeducation) or for people with certain characteristics.

Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models.

Phishing is one of the most dangerous attacks targeting individuals, organizations, and nations. Although many traditional methods for email phishing detection exist, there is a need to improve accuracy and reduce false-positive rates. Our work investigates one-dimensional CNN-based models (1D-CNNPD) to detect phishing emails in order to address these challenges. Additionally, further improvement is achieved with the augmentation of the base 1D-CNNPD model with recurrent layers, namely, LSTM, Bi-LSTM, GRU, and Bi-GRU, and experimented with the four resulting models. Two benchmark datasets were used to evaluate the performance of our models: Phishing Corpus and Spam Assassin. Our results indicate that, in general, the augmentations improve the performance of the 1D-CNNPD base model. Specifically, the 1D-CNNPD with Bi-GRU yields the best results. Overall, the performance of our models is comparable to the state of the art of CNN-based phishing email detection. The Advanced 1D-CNNPD with Leaky ReLU and Bi-GRU achieved 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. We observe that increasing model depth typically leads to an initial performance improvement, succeeded by a decline. In conclusion, this study highlights the effectiveness of augmented 1D-CNNPD models in detecting phishing emails with improved accuracy. The reported performance measure values indicate the potential of these models in advancing the implementation of cybersecurity solutions to combat email phishing attacks.

Characterizing participants who respond to text, email, phone calls, or postcards in a SARS-CoV-2 prevalence study.

INTRODUCTION: Multiple modalities and frequencies of contact are needed to maximize recruitment in many public health surveys. The purpose of this analysis is to characterize respondents to a statewide SARS-CoV-2 testing study whose participation followed either postcard, phone outreach or electronic means of invitation. In addition, we examine how participant characteristics differ based upon the number of contacts needed to elicit participation. METHODS: This is a cross-sectional analysis of survey data collected from participants who were randomly selected to represent Indiana residents and were invited to be tested for Covid-19 in April 2020. Participants received invitations via postcard, text/emails, and/or robocalls/texts based upon available contact information. The modality, and frequency of contacts, that prompted participation was determined by when the notification was sent and when the participant responded and subsequently registered to participate in the study. Chi square analyses were used to determine differences between groups and significant findings were analyzed using multinomial logistic regression. RESULTS: Respondents included 3,658 individuals and were stratified by postcards (7.9%), text/emails (26.5%), and robocalls/text (65.7%) with 19.7% registering after 1 contact, 47.9% after 2 contacts, and 32.4% after 3 contacts encouraging participation. Females made up 54.6% of the sample and responded at a higher rate for postcards (8.2% vs. 7.5%) and text/emails (28.1 vs. 24.6%) as compared to males (χ2 = 7.43, p = 0.025). Compared to males, females responded at a higher percentage after 1 contact (21.4 vs. 17.9%, χ2 = 7.6, p = 0.023). Those over 60 years responded most often after 2 contacts (χ2 = 27.5, p < 0.001) when compared to others at younger age groups. In regression analysis, participant sex (p = 0.036) age (p = 0.005), educational attainment (p = < 0.0001), and being motivated by "free testing" (p = 0.036) were correlated with participation in the prevalence study. DISCUSSION: Researchers should be aware that the modality of contact as well as the number of prompts used could influence differential participation in public health studies. Our findings can inform researchers developing studies that rely on selective participation by study subjects. We explore how to increase participation within targeted demographic groups using specific modalities and examining frequency of contact.

Improving undergraduate students' email etiquette with computer-based instruction.

Email etiquette is an important skill, especially in professional settings. Research demonstrates that undergraduate students follow email rules when given written instructions plus an example. The purpose of the present study was to evaluate the effects of computer-based email instruction on undergraduate students' email etiquette and to assess the social validity of that instruction. The email instruction package was delivered through an online learning management system and consisted of written instructions plus a model, a quiz, and quiz feedback. We measured email etiquette by scoring emails from course assignments using a checklist. The instruction package produced a replicated increase in mean email checklist scores across two sections of introductory psychology, and checklist scores were elevated when participants sent emails in a novel context. The results of the social-validity assessments suggest that the goals were important, the procedures were acceptable, and there were meaningful improvements in email etiquette for some participants.

Likelihood ratios for changepoints in categorical event data with applications in digital forensics.

We investigate likelihood ratio models motivated by digital forensics problems involving time-stamped user-generated event data from a device or account. Of specific interest are scenarios where the data may have been generated by a single individual (the device/account owner) or by two different individuals (the device/account owner and someone else), such as instances in which an account was hacked or a device was stolen before being associated with a crime. Existing likelihood ratio methods in this context require that a precise time is specified at which the device or account is purported to have changed hands (the changepoint)-this is the known changepoint likelihood ratio model. In this paper, we develop a likelihood ratio model that instead accommodates uncertainty in the changepoint using Bayesian techniques, that is, an unknown changepoint likelihood ratio model. We show that the likelihood ratio in this case can be calculated in closed form as an expression that is straightforward to compute. In experiments with simulated changepoints using real-world data sets, the results demonstrate that the unknown changepoint model attains comparable performance to the known changepoint model that uses a perfectly specified changepoint, and considerably outperforms the known changepoint model that uses a misspecified changepoint, illustrating the benefit of capturing uncertainty in the changepoint.

BEC Defender: QR Code-Based Methodology for Prevention of Business Email Compromise (BEC) Attacks.

In an era of ever-evolving and increasingly sophisticated cyber threats, protecting sensitive information from cyberattacks such as business email compromise (BEC) attacks has become a top priority for individuals and enterprises. Existing methods used to counteract the risks linked to BEC attacks frequently prove ineffective because of the continuous development and evolution of these malicious schemes. This research introduces a novel methodology for safeguarding against BEC attacks called the BEC Defender. The methodology implemented in this paper augments the authentication mechanisms within business emails by employing a multi-layered validation process, which includes a MAC address as an identity token, QR code generation, and the integration of timestamps as unique identifiers. The BEC-Defender algorithm was implemented and evaluated in a laboratory environment, exhibiting promising results against BEC attacks by adding an extra layer of authentication.

Associations of Depression/Anxiety with Technology Use, Discontinued Use, and Nonuse in Older Adults.

OBJECTIVES: To examine correlates of the changes in technology use among older adults and the associations of depression/anxiety symptoms with technology use changes. METHODS: We used the 2019-2021 U.S. National Health and Aging Trends Study (N = 3,063; age 70+). We fitted multinomial logistic regression models to examine: (1) correlates of never use and discontinued use versus use of email/texting and the internet during the 3-year study period; and (2) associations of past-month depression/anxiety symptoms in 2021 with use and discontinued use versus never use of email/texting and social network site (SNS). RESULTS: The findings show age, socioeconomic, and health barriers to technology use. Email/texting and SNS use in 2021, compared to never use in all 3 years, was associated with a lower likelihood of moderate/severe depression/anxiety symptoms in 2021 (RRR = 0.54, 95% CI = 0.37-0.81 for email/texting use; RRR = 0.56, 95% CI = 0.33-0.97 for SNS use). Video calls with family/friends were not associated with depression/anxiety symptoms. CONCLUSIONS: The findings expand the existing knowledge base regarding potential impact of technology use on mental health beyond the early months of the COVID-19 pandemic. CLINICAL IMPLICATIONS: More concerted efforts are warranted to help older adults' technology uptake and continued use and to promote mental health benefits of technology use.

Exploring User Perspectives on Brief Reflective Questioning Activities for Stress Management: Mixed Methods Study.

BACKGROUND: Current online interventions dedicated to assisting individuals in managing stress and negative emotions often necessitate substantial time commitments. This can be burdensome for users, leading to high dropout rates and reducing the effectiveness of these interventions. This highlights an urgent need for concise digital activities that individuals can swiftly access during instances of negative emotions or stress in their daily lives. OBJECTIVE: The primary aim of this study was to investigate the viability of using a brief digital exercise, specifically a reflective questioning activity (RQA), to help people reflect on their thoughts and emotions about a troubling situation. The RQA is designed to be quick, applicable to the general public, and scalable without requiring a significant support structure. METHODS: We conducted 3 simultaneous studies. In the first study, we recruited 48 participants who completed the RQA and provided qualitative feedback on its design through surveys and semistructured interviews. In the second study, which involved 215 participants from Amazon Mechanical Turk, we used a between-participants design to compare the RQA with a single-question activity. Our hypotheses posited that the RQA would yield greater immediate stress relief and higher perceived utility, while not significantly altering the perception of time commitment. To assess these, we measured survey completion times and gathered multiple self-reported scores. In the third study, we assessed the RQA's real-world impact as a periodic intervention, exploring engagement via platforms such as email and SMS text messaging, complemented by follow-up interviews with participants. RESULTS: In our first study, participants appreciated the RQA for facilitating structured reflection, enabling expression through writing, and promoting problem-solving. However, some of the participants experienced confusion and frustration, particularly when they were unable to find solutions or alternative perspectives on their thoughts. In the second study, the RQA condition resulted in significantly higher ratings (P=.003) for the utility of the activity and a statistically significant decrease (P<.001) in perceived stress rating compared with the single-question activity. Although the RQA required significantly more time to be completed (P<.001), there was no statistically significant difference in participants' subjective perceived time commitment (P=.37). Deploying the RQA over 2 weeks in the third study identified some potential challenges to consider for such activities, such as the monotony of doing the same activity several times, the limited affordances of mobile phones, and the importance of having the prompts align with the occurrence of new troubling situations. CONCLUSIONS: This paper describes the design and evaluation of a brief online self-reflection activity based on cognitive behavioral therapy principles. Our findings can inform practitioners and researchers in the design and exploration of formats for brief interventions to help people with everyday struggles.

Content analysis of IQOS direct mail and email marketing in the US.

Objective: Novel nicotine and tobacco products, including heated tobacco products (HTPs) like IQOS, are growing in global popularity. IQOS was the first HTP authorized for sale by the US Food and Drug Administration, entering the US market in 2019 and being removed in 2021 due to patent-related legal challenges, with the possibility of returning in 2024. Direct marketing is one method tobacco companies use to reach consumers of these products. The purpose of this study was to investigate the content of US IQOS direct mail and email marketing. Methods: Direct marketing items were collected between September 2019 and July 2021 by seven team members in the first US IQOS test market, Atlanta, Georgia. Results: Overall, 101 marketing items were collected, 59 of which were unique. Among the unique items that showed images of persons ("models"), 70 % showed models appearing to be from racial/ethnic minoritized groups, 86.8 % showed at least one female-presenting model, and 37.5 % showed models appearing to be young adults (18-29 years). Items often had an embedded link/URL (91.5 %) and mentioned topics such as online services (54.2 %; for example, online ordering and tutorials), user experience (49.2 %), social media (44.1 %), and purchasing locations (37.3 %). When examined for their main purpose, items focused on subjects such as store experience (37.7 %), product introduction (18.6 %), and product use (15.3 %). Conclusions: Our study highlights the importance of better understanding how novel tobacco products are marketed, which can inform policymakers' regulatory efforts and product authorization decisions.

My time, your time, our time. Older patients' and GPs' time sensibilities around email consultations.

In this study, we discuss how email consultations in general practice operate as a temporal technology, transforming working conditions and power relations between general practitioners (GPs) and patients. We draw on empirical material from Denmark in the form of a set of semi-structured interviews with 53 patients and 15 GPs, including two focus group discussions with 17 GPs. Our theoretical point of departure stems primarily from media theorist Sarah Sharma's (2014) concept of power-chronography, which describes how power is embedded in temporal relations and everyday life and secondarily from sociologist, Judy Wajcman's (2015) concept of multiple temporal landscapes. Patients and GPs calibrate their own time and attune their mutual time according to their expectations and ideas about the other party's time. The patient and the GP can both be viewed as 'time workers' and the email consultation as a digital technology fostering the recalibration of one person's time to that of another, requiring significant labour. The email consultation rearranges the GP-patient boundaries and thereby the power relations. Health institutions ought to consider whose time and labour is being 'saved' with digital systems.

The use of social media networks for healthy nutritional practices by deaf and hearing students.

Background: Social media networks such as Facebook, Twitter, WhatsApp, and YouTube are among the most commonly used social networks among people. If used properly, they can contribute to enhancing individual knowledge and scientific values. Aim: The study aimed to investigate the use of social media networks for healthy nutritional practices among deaf and hearing students. Methods: The sample of the study consisted of 103 students (50 deaf and 53 hearing). The researchers used a descriptive approach and adopted a questionnaire for data collection. Results: The findings of the study showed that the use of social media networks for healthy nutritional practices among deaf and hearing students was at a moderate level. However, there were statistically significant gender differences in the average responses of deaf and hearing students in the use of social media networks for healthy nutritional practices. For the status of students (deaf and hearing students), there were statistically significant differences in the average responses to the use of social media networks for healthy nutritional practices. Conclusion: Social media networks play an important role in raising awareness and promoting healthy nutrition practices for both deaf and hearing students.

E-mail as a way of communication during the ACWY meningococcal vaccination campaign in adolescents and young adults in the Region of Murcia.

In 2019, ACWY meningococcal vaccination for people born between 2001 and 2007 was recommended. In Murcia, during the first 9 months, the coverage was 52.89%. This study is aimed to evaluate the effects of e-mail reminders on vaccination coverage. A longitudinal, prospective trial was performed on non-vaccinated individuals with e-mail addresses. An e-mail reminder was sent to people assigned to the intervention group (born in any month, except January and July), and 4 weeks later, the same was sent to the control group. Vaccination coverage was assessed before and 4 weeks after each intervention. After the first intervention, 5.15% of the participants in the intervention group were vaccinated (1.57% in the control group). The increased likelihood of being vaccinated if a person had been sent an e-mail was 1.033 (95% confidence interval, 1.019-1.047; p = 0.001). This study highlighted the impact of e-mail as an appropriate method of communication for vaccination programmes.

Behind the Bait: Delving into PhishTank's hidden data.

Phishing constitutes a form of social engineering that aims to deceive individuals through email communication. Extensive prior research has underscored phishing as one of the most commonly employed attack vectors for infiltrating organizational networks. A prevalent method involves misleading the target by employing phishing URLs concealed through hyperlink strategies. PhishTank, a website employing the concept of crowd-sourcing, aggregates phishing URLs and subsequently verifies their authenticity. In the course of this study, we leveraged a Python script to extract data from the PhishTank website, amassing a comprehensive dataset comprising over 190,0000 phishing URLs. This dataset is a valuable resource that can be harnessed by both researchers and practitioners for enhancing phish- ing filters, fortifying firewalls, security education, and refining training and testing models, among other applications.

Email-Based Recruitment Into the Health eHeart Study: Cohort Analysis of Invited Eligible Patients.

BACKGROUND: Web- or app-based digital health studies allow for more efficient collection of health data for research. However, remote recruitment into digital health studies can enroll nonrepresentative study samples, hindering the robustness and generalizability of findings. Through the comprehensive evaluation of an email-based campaign on recruitment into the Health eHeart Study, we aim to uncover key sociodemographic and clinical factors that contribute to enrollment. OBJECTIVE: This study sought to understand the factors related to participation, specifically regarding enrollment, in the Health eHeart Study as a result of a large-scale remote email recruitment campaign. METHODS: We conducted a cohort analysis on all invited University of California, San Francisco (UCSF) patients to identify sociodemographic and clinical predictors of enrollment into the Health eHeart Study. The primary outcome was enrollment, defined by account registration and consent into the Health eHeart Study. The email recruitment campaign was carried out from August 2015 to February 2016, with electronic health record data extracted between September 2019 and December 2019. RESULTS: The email recruitment campaign delivered at least 1 email invitation to 93.5% (193,606/206,983) of all invited patients and yielded a 3.6% (7012/193,606) registration rate among contacted patients and an 84.1% (5899/7012) consent rate among registered patients. Adjusted multivariate logistic regression models analyzed independent sociodemographic and clinical predictors of (1) registration among contacted participants and (2) consent among registered participants. Odds of registration were higher among patients who are older, women, non-Hispanic White, active patients with commercial insurance or Medicare, with a higher comorbidity burden, with congestive heart failure, and randomized to receive up to 2 recruitment emails. The odds of registration were lower among those with medical conditions such as dementia, chronic pulmonary disease, moderate or severe liver disease, paraplegia or hemiplegia, renal disease, or cancer. Odds of subsequent consent after initial registration were different, with an inverse trend of being lower among patients who are older and women. The odds of consent were also lower among those with peripheral vascular disease. However, the odds of consent remained higher among patients who were non-Hispanic White and those with commercial insurance. CONCLUSIONS: This study provides important insights into the potential returns on participant enrollment when digital health study teams invest resources in using email for recruitment. The findings show that participant enrollment was driven more strongly by sociodemographic factors than clinical factors. Overall, email is an extremely efficient means of recruiting participants from a large list into the Health eHeart Study. Despite some improvements in representation, the formulation of truly diverse studies will require additional resources and strategies to overcome persistent participation barriers.

Effect of Personalized Email-Based Reminders on Participants' Timeliness in an Online Education Program: Randomized Controlled Trial.

BACKGROUND: Postsecondary students need to be able to handle self-regulated learning and manage schedules set by instructors. This is particularly the case with online courses, as they often come with a limited number of social reminders and less information directly from the teacher compared to courses with physical presence. This may increase procrastination and reduce timeliness of the students. Reminders may be a tool to improve the timeliness of students' study behavior, but previous research shows that the effect of reminders differs between types of reminders, whether the reminder is personalized or general, and depending on the background of the students. In the worst cases, reminders can even increase procrastination. OBJECTIVE: The aim of this study was to test if personalized email reminders, as compared to general email reminders, affect the time to completion of scheduled online coursework. The personalized reminders included information on which page in the online material the participants ought to be on at the present point in time and the last page they were on during their last session. The general reminders only contained the first part of this information: where they ought to be at the present point in time. METHODS: Weekly email reminders were sent to all participants enrolled in an online program, which included 39 professional learners from three East African countries. All participants in the Online Education for Leaders in Nutrition and Sustainability program, which uses a question-based learning methodology, were randomly assigned to either personalized or general reminders. The structure of the study was AB-BA, so that group A received personalized reminders for the first unit, then general reminders for the rest of the course, while group B started with general reminders and received personalized reminders only in the third (and last) unit in the course. RESULTS: In total, 585 email reminders were distributed, of which 390 were general reminders and 195 were personalized. A Bayesian mixed-effects logistic regression was used to estimate the difference in the probability of being on time with one's studies. The probability of being on time was 14 percentage points (95% credible interval 3%-25%) higher following personalized reminders compared to that following general reminders. For a course with 100 participants, this means 14 more students would be on time. CONCLUSIONS: Personalized reminders had a greater positive effect than general reminders for a group of adults working full-time while enrolled in our online educational program. Considering how small the intervention was-adding a few words with the page number the student ought to be on to a reminder-we consider this effect fairly substantial. This intervention could be repeated manually by anyone and in large courses with some basic programming.

A non-randomised feasibility study of a mHealth follow-up program in bariatric surgery.

BACKGROUND: Behavioural support via mobile health (mHealth) is emerging. This study aimed to assess the feasibility, acceptability, cost, and potential effect on weight of a mHealth follow-up program in bariatric surgery. METHODS: This was a non-randomised feasibility study describing intervention development and proof in the concept of a mHealth follow-up program in bariatric surgery. The study compares a prospective cohort with a historical control group and was conducted in a tertiary bariatric surgery service in Australia. The intervention group included individuals who had bariatric surgery (2019-2021) and owned a smart device, and the historical control group received usual postoperative care (2018). The intervention involved usual care plus codesigned biweekly text messages, monthly email newsletters, and online resources/videos over a 6-month period. The primary outcome measures included feasibility (via recruitment and retention rate), acceptability (via mixed methods), marginal costs, and weight 12 months postoperatively. Quantitative analysis was performed, including descriptive statistics and inferential and regression analysis. Multivariate linear regression and mixed-effects models were undertaken to test the potential intervention effect. Qualitative analysis was performed using inductive content analysis. RESULTS: The study included 176 participants (n = 129 historical control, n = 47 intervention group; mean age 56 years). Of the 50 eligible patients, 48 consented to participate (96% recruitment rate). One participant opted out of the mHealth program entirely without disclosing their reason (98% retention rate). The survey response rate was low (n = 16/47, 34%). Participants agreed/strongly agreed that text messages supported new behaviours (n = 13/15, 87%); however, few agreed/strongly agreed that the messages motivated goal setting and self-monitoring (n = 8/15, 53%), dietary change (n = 6/15, 40%), or physical activity (n = 5/15, 33%). Interviews generated four main themes (n = 12): 'motivators and expectations', 'preferences and relevance', 'reinforced information", and 'wanting social support'. The intervention reinforced information, email newsletters were lengthy/challenging to read, and text messages were favoured, yet tailoring was recommended. The intervention cost AUD 11.04 per person. The mean 12-month weight was 86 ± 16 kg and 90 ± 16 kg (intervention and historical control) with no statistically significant difference. Intervention recipients enrolled at 3 months postoperatively demonstrated a statistically significant difference in 12-month weight (p = 0.014). CONCLUSION: Although this study observed high rates of recruitment and retention, findings should be considered with caution as mHealth may have been embraced more by the intervention cohort as a result of the 2019 coronavirus pandemic. Of the various digital strategies developed and tested, the text message approach was the most acceptable; however, future intervention iterations could be strengthened through tailoring information when possible. The use of email newsletters and online resources/videos requires further testing of effectiveness to determine their value for continued use in bariatric surgery services.

A randomized controlled trial of post-donation communication materials to increase donor return following a vasovagal reaction.

BACKGROUND: Vasovagal reactions (VVRs) are one of the primary reasons for people to stop donating blood. The aim of this study was to evaluate the impact of newly developed online communications on the rate of return of whole-blood (WB) and plasma donors who experienced a VVR. STUDY DESIGN AND METHODS: First-time and experienced WB and plasma donors who had a VVR without a loss of consciousness in the previous 3 days were randomly allocated to receive (a) an SMS sent 1-4 days post-VVR (n = 2303), (b) an email sent 6-10 days post-VVR (n = 2360), (c) both the SMS and the email (n = 2248), or (d) business-as-usual donor retention communications (control; n = 2557). Donation data were extracted to determine subsequent donation attempts. RESULTS: For return within 3 months, WB donors in the Email Only condition had significantly increased odds of returning (OR: 1.26, 95%CI: 1.01-1.56). Subgroup analysis within WB donors showed increased odds of return for women sent the SMS and Email (OR: 1.50, 95%CI: 1.14-1.96) or the Email Only (OR: 1.44, 95%CI: 1.10-1.89), and for first-time donors sent the Email Only (OR: 1.48, 95%CI: 1.07-2.05). At 6 months, only first-time WB donors in the Email Only condition had significantly increased odds of returning (OR: 1.30, 95%CI: 1.01-1.69). No significant effects of the intervention were found for immediate or intermediate return for plasma donors. DISCUSSION: Sending an email addressing common donor concerns regarding VVRs increases WB donor retention, but additional strategies are needed for the effects to last and to retain plasma donors.

A novel approach for Arabic business email classification based on deep learning machines.

During the last decades, the reliance on email communication, especially in business, has increased significantly. Companies receive a massive amount of emails daily, that include business inquiries, customers' feedback, and other types of emails. This inspired many researchers to propose different algorithms to classify and redistribute the numerous emails according to their content. Nowadays, emails containing Arabic text, especially in the Arab world, have raised an increasing concern since they became widely used in official correspondence. Nevertheless, just a small amount of literature focuses on Arabic text classification. Therefore, this work addresses Arabic business emails classification based on natural language processing (NLP). A dataset of 63,257 emails was used and the emails were classified as: urgency, sentiment, and topic classification. The proposed models are based on machine learning techniques and a lexicon of words on which the emails are identified. The models are composed of different settings of convolutional neural networks (CNN). A separate model was built, trained, and tested for each category. The results were promising and gave an accuracy of about 92% and a loss of less than 8%. They also proved the correctness and robustness of this work.