Email Data Research Articles

Email Analysis in Fraud Investigation: Digital Forensic and Network Analysis Approach

Email is an imperative method of communication that is changing the way people share their data and information. It provides effective and efficient communication, especially in business, convenience, and easy access and replication. Those electronic data should be considered by a fraud investigator to comprehend the investigation. Email can be divided into two parts: the head of the email and the email body. The head of the email is metadata that consists of unstructured data, and the body and its attachment consist of semi-structured data. The email data usually comes in large volumes and ranges of types. Therefore, a manual investigation of an email should be avoided. This paper uses the Design Science Research Methodology to discover the most profound framework in an email fraud investigation. Using email metadata and email body, this research performs a digital forensic framework: preparation, gathering, processing, and presentation, combines with social network analysis to be applicable in the investigation. The result shows that digital forensics process, network analysis, data visualization provides a more valuable and comprehensive insight into email analysis.

Are lifestyle changes from online information associated with discussing the information with a doctor? A cross -sectional study.

BackgroundThe prevalence of diabetes and the use of electronic health (eHealth) are increasing. Lifestyle changes in a positive direction may reduce morbidity and mortality in patients with diabetes. The main objective of this study was to test the association between lifestyle changes based on online information seeking and discussing the information with a doctor.MethodsIn this cross-sectional study we used e-mail survey data from 1250 members of The Norwegian Diabetes Association, collected in 2018. Included in the analyses were 847 men and women aged 18 to 89 years diagnosed with diabetes and who reported use of eHealth within the previous year. We used descriptive statistics to estimate lifestyle changes based on information from the internet. Logistic regressions were used to estimate the associations between lifestyle changes after online information seeking and discussing the information with a doctor. Analyses were adjusted for gender, age, education, and self-rated health.ResultsLifestyle changes accomplished after online information seeking was reported by 46.9% (397/847) of the participants. The odds of changing lifestyle were more than doubled for those who had discussed information from the internet with a doctor (odds ratio 2.54, confidence interval 1.90–3.40). The odds of lifestyle changes were lower in the age groups 30–39 years and 60 years and over, compared to those aged 18–29 years (the reference group). Lifestyle changes were not associated with gender, education, or self-rated health.ConclusionsOur findings indicate that health-care professionals can play an important role in lifestyle changes additional to health-advice found on the internet. This study underlines the importance of easily accessible high-quality online information, as well as the importance of making room for discussing lifestyle in the clinical encounter.

Analysis of the Emails From the Dutch Web-Based Intervention "Alcohol de Baas": Assessment of Early Indications of Drop-Out in an Online Alcohol Abuse Intervention.

Nowadays, traditional forms of psychotherapy are increasingly complemented by online interactions between client and counselor. In (some) web-based psychotherapeutic interventions, meetings are exclusively online through asynchronous messages. As the active ingredients of therapy are included in the exchange of several emails, this verbal exchange contains a wealth of information about the psychotherapeutic change process. Unfortunately, drop-out-related issues are exacerbated online. We employed several machine learning models to find (early) signs of drop-out in the email data from the “Alcohol de Baas” intervention by Tactus. Our analyses indicate that the email texts contain information about drop-out, but as drop-out is a multidimensional construct, it remains a complex task to accurately predict who will drop out. Nevertheless, by taking this approach, we present insight into the possibilities of working with email data and present some preliminary findings (which stress the importance of a good working alliance between client and counselor, distinguish between formal and informal language, and highlight the importance of Tactus' internet forum).

128 Evaluation of a Secure Messaging System for Children with Medical Complexity

Abstract Primary Subject area Complex Care Background The Connecting2gether (C2) platform is a secure online information-sharing tool that aims to improve care for Children with Medical Complexity (CMC) and their families. A key feature of C2 is secure messaging that enables parents to communicate with their child’s healthcare providers (HCPs) in an easy and timely manner. Objectives The objectives of this project are to (1) describe the usage of the secure messaging system; and (2) conduct a thematic comparative evaluation of the secure messaging tool, and email and phone calls. Design/Methods This study is a sub-component of a larger project investigating the overall feasibility and acceptability of the C2 platform. Parents of CMC were recruited from a tertiary level Complex Care program to use the C2 platform for a period of 6 months. Messaging data was extracted from C2 usage reports, and phone and email documentation was extracted from the patient’s electronic medical record. Codes were developed iteratively through comprehensive review of the C2 messages. Message, phone, and email data were then coded by two investigators using thematic analysis. Quantitative data from C2 usage reports were analyzed using descriptive statistics. Results Thirty-four parents and 90 care team members, including HCPs, family, and patient information coordinators were registered on the platform. 4027 messages were exchanged on C2. On average, parents sent 33.4 messages and received 66.4 messages on C2. Of all messages on C2, 32.6% were related to comments, questions, and concerns about the platform itself and its features. Figure 1 demonstrates the thematic content of messages related to care, and highlights the differences in messaging content between the 3 forms of communication. Email and phone content focused primarily on clinical care whereas C2 messaging content also emphasized other aspects of care including education, provision of resources, and personal support. Conclusion This study demonstrates the role that a secure messaging system can have for parents of CMC in being active members of their child’s care. Phone and email were mostly used to discuss medications or clinical issues, whereas C2 enabled the discussion of the patient as a whole. The use of secure messaging can therefore complement other forms of communication between providers and families, instead of replacing them. Further research is needed to understand clinical outcomes associated with the use of secure messaging in order to understand its role in improving patient care and overall caregiver and provider experience.

A Novel Real-time Anti-spam Framework

As one of the most pervasive current modes of communication, email needs to be fast and reliable. However, spammers and attackers use it as a primary channel to conduct illegal activities. Although many approaches have been developed and evaluated for spam detection, they do not provide sufficient accuracy. This deficiency results in significant economic losses for organizations. In this article, we first propose a framework for creating novel spam filters using Keras to combine a Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) classification models. We then use this framework to introduce a specific solution applicable to realistic scenarios involving dynamic incoming email data in real-time. This solution takes the form of a real-time content-based spam classifier. We evaluate its performance concerning accuracy, precision, recall, false-positive, and false-negative rates. Our experimental results show that our approach can significantly outperform existing solutions for real-time spam detection.

Combining Content and Social Features in a Deep Learning Approach to Vietnamese Email Prioritization

The email overload problem has been discussed in numerous email-related studies. One of the possible solutions to this problem is email prioritization, which is the act of automatically predicting the importance levels of received emails and sorting the user’s inbox accordingly. Several learning-based methods have been proposed to address the email prioritization problem using content features as well as social features. Although these methods have laid the foundation works in this field of study, the reported performance is far from being practical. Recent works on deep neural networks have achieved good results in various tasks. In this paper, the authors propose a novel email prioritization model which incorporates several deep learning techniques and uses a combination of both content features and social features from email data. This method targets Vietnamese emails and is tested against a self-built Vietnamese email corpus. Conducted experiments explored the effects of different model configurations and compared the effectiveness of the new method to that of a previous work.

Latent Set Models for Two-Mode Network Data

Two-mode networks are a natural representation for many kinds of relational data. These networks are bipartite graphs consisting of two distinct sets ("modes") of entities. For example, one can model multiple recipient email data as a two-mode network of (a) individuals and (b) the emails that they send or receive. In this work we present a statistical model for two-mode network data which posits that individuals belong to latent sets and that the members of a particular set tend to co-appear. We show how to infer these latent sets from observed data using a Markov chain Monte Carlo inference algorithm. We apply the model to the Enron email corpus, using it to discover interpretable latent structure as well as evaluating its predictive accuracy on a missing data task. Extensions to the model are discussed that incorporate additional side information such as the email's sender or text content, further improving the accuracy of the model.

Impact of Entity Disambiguation Errors on Social Network Properties

Entities in social networks may be subject to consolidation when they are inconsistently indexed, and subject to splitting when multiple entities share the same name. How much do errors or shortfalls in entity disambiguation distort network properties? We show empirically how network analysis results and derived implications can tremendously change depending solely on entity resolution techniques. We present a series of controlled experiments where we vary disambiguation accuracy to study error propagation and the robustness of common network metrics, topologies and key players. Our results suggest that for email data, not conducting deduplication, e.g. when operating on the level of email addressed instead of individuals, can make organizational communication networks appear to be less coherent and integrated as well as bigger than they truly are. For co-publishing networks, improper merging as caused by the commonly used initial based disambiguation techniques can make a scientific sector seem more dense and cohesive than it really is, and individual authors appear to be more productive, collaborative and diversified than they actually are. Disambiguation errors can also lead to the false detection of power law distributions of node degree; suggesting preferential attachment processes that might not apply.

A Large-Scale Comparative Study of Informal Social Networks in Firms

Theories of organizations are sympathetic to long-standing ideas from network science that organizational networks should be regarded as multiscale and capable of displaying emergent properties. However, the historical difficulty of collecting individual-level network data for many (N ≫ 1) organizations, each of which comprises many (n ≫ 1) individuals, has hobbled efforts to develop specific, theoretically motivated hypotheses connecting micro- (i.e., individual-level) network structure with macro-organizational properties. In this paper we seek to stimulate such efforts with an exploratory analysis of a unique data set of aggregated, anonymized email data from an enterprise email system that includes 1.8 billion messages sent by 1.4 million users from 65 publicly traded U.S. firms spanning a wide range of sizes and 7 industrial sectors. We uncover wide heterogeneity among firms with respect to all measured network characteristics, and we find robust network and organizational variation as a result of size. Interestingly, we find no clear associations between organizational network structure and firm age, industry, or performance; however, we do find that centralization increases with geographical dispersion—a result that is not explained by network size. Although preliminary, these results raise new questions for organizational theory as well as new issues for collecting, processing, and interpreting digital network data. This paper was accepted by David Simchi-Levi, Special Section of Management Science: 65th Anniversary.

Disability and Academic Careers: Using the Social Relational Model to Reveal the Role of Human Resource Management Practices in Creating Disability

Disabled people continue to face a variety of significant barriers to full participation and inclusion in work and employment. However, their experiences remain only sparsely discussed in relation to human resource management (HRM) practices and employment contexts. The current study contributes to this gap in understanding by drawing together relevant work connecting HRM practices, diversity management and disability studies to examine the experiences of a sample of 75 disabled academics in the UK. Through the social relational model of disability, HRM practices socially construct disability in the workplace. Interview and email data from disabled academics in the UK are drawn upon to illustrate how organisational practices and policies, while intended to ‘accommodate’ disabled people, inadvertently construct and shape disability for people with impairments or chronic health conditions.

Sequence encoding incorporated CNN model for Email document sentiment classification

Document sentiment classification is an area of study that has been developed for decades. However, sentiment classification of Email data is rather a specialized field that has not yet been thoroughly studied. Compared to typical social media and review data, Email data has characteristics of length variance, duplication caused by reply and forward messages, and implicitness in sentiment indicators. Due to these characteristics, existing techniques are incapable of fully capturing the complex syntactic and relational structure among words and phrases in Email documents.In this study, we introduce a dependency graph-based position encoding technique enhanced with weighted sentiment features, and incorporate it into the feature representation process. We combine encoded sentiment sequence features with traditional word embedding features as input for a revised deep CNN model for Email sentiment classification. Experiments are conducted on three sets of real Email data with adequate label conversion processes. Empirical results indicate that our proposed SSE-CNN model obtained the highest accuracy rate of 88.6%, 74.3% and 82.1% for three experimental Email datasets over other comparative state-of-the-art algorithms. Furthermore, our performance evaluations on the preprocessing and sentiment sequence encoding justify the effectiveness of Email preprocessing and sentiment sequence encoding with dependency-graph based position and SWN features on the improvement of Email document sentiment classification.

Comparison of Deep and Traditional Learning Methods for Email Spam Filtering

Electronic mail, or email, is a method for com-municating using the internet which is inexpensive, effective, and fast. Spam is a type of email where unwanted messages, usually unwanted commercial messages, are distributed in large quantities by a spammer. The objective of such behavior is to harm email users; these messages need to be detected and prevented from being sent to users in the first place. In order to filter these emails, the developers have used machine learning methods. This paper discusses different methods which are used deep learning methods such as a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models with(out) a GloVe model in order to classify spam and non-spam messages. These models are only based on email data, and the extraction set of features is automatic. In addition, our work provides a comparison between traditional machine learning and deep learning algorithms on spam datasets to find out the best way to intrusion detection. The results indicate that deep learning offers improved performance of precision, recall, and accuracy. As far as we are aware, deep learning methods show great promise in being able to filter email spam, therefore we have performed a comparison of various deep learning methods with traditional machine learning methods. Using a benchmark dataset consisting of 5,243 spam and 16,872 not-spam and SMS messages, the highest achieved accuracy score is 96.52% using CNN with the GloVe model.

Personally Identifiable Information (PII) Detection in the Unstructured Large Text Corpus using Natural Language Processing and Unsupervised Learning Technique

Personally Identifiable Information (PII) has gained much attention with the rapid development of technologies and the exploitation of information relating to an individual. The corporates and other organizations store a large amount of information that is primarily disseminated in the form of emails that include personnel information of the user, employee, and customers. The security aspects of PII storage have been ignored, raising serious security concerns onindividual privacy. A significant concern arises about comprehending the responsibilities regarding the uses of PII. However, in real-time scenarios, email data is regarded as unstructured text data, detecting PII from such an unstructured large text corpus is quite challenging. This paper presents an intelligent clustering approach for automatically detecting personally identifiable information (PII) from a large text corpus. The focus of the proposed study is to design a model that receives text content and detects possible PII attributes. Therefore, this paper presents a clustering-based PII Model (C-PPIM) based on NLP and unsupervised learning to address detection of PII in the unstructured large text corpus. NLP is used to perform topic modeling, and Byte mLSTM, a different approach of sequence model, is implemented to address clustering problems in PII detection. The performance analysis of the proposed model is carried out existing hierarchical clustering concerning silhouette and cohesion score. The outcome indicatedthe effectiveness of the proposed system that highlights significant PII attributes, with significant scope in real-time implementation. In contrast, existing techniques are too expensive to function and fit in real-time environments.

Survey and Review

Our Survey and Review paper, “The Why, How, and When of Representations for Complex Systems,” by Leo Torres, Ann S. Blevins, Danielle Bassett, and Tina Eliassi-Rad, lists 233 references. Some of them were published in applied mathematics journals, like SIAM Review or SIAM Journal on Applied Algebra and Geometry. Others appeared in well-known “pure” mathematics journals, including Annals of Mathematics and Bulletin of the American Mathematical Society. There are many references to multidisciplinary outlets like Science, Nature, or Proceedings of the National Academy of Sciences of the USA. But the whole list is astonishing: from the Journal of the Acoustical Society of America to Sociometry to Human Brain Mapping. This diversity of journals is obviously due to the interest in complex systems that now exists in a wide variety of applications. A complex system is a collection of a large number of objects or agents that interact with one another in a way that gives rise to the emergence of collective behaviors not immediately predictable from the aggregation of the individual behaviors of the parts. The generality of this definition---the objects may be anything from molecules in a cell to businesses in the economy of a country---makes it possible for complex system theory to be useful in a large variety of fields, as described above. On the flip side, a theory that is spread over such a diversity of application areas may easily be compartmentalized. The aim of the review in this issue is to propose a common language to increase the cohesion of the theory. Three alternative approaches to the representation of complex systems are discussed in detail: graphs, simplicial complexes, and hypergraphs. The main ideas are illustrated by means of more than a dozen figures, and the paper closes with two real-world examples using coauthorship data and email communication data. In addition to being useful for complex system scientists wishing to broaden their view of the theory, the survey provides an accessible introduction to the field.

АСПЕКТИ КІБЕРБЕЗПЕКИ ПЛАТФОРМ ДИСТАНЦІЙНОГО НАВЧАННЯ

The subject of study in the article is the platforms used to organize the educational process in the context of distance learning. The following platforms are selected: learning content management systems (open source systems and individual development), Google Classroom service, e-mail, and cloud data storage. The objects of the educational process for which the security state must be provided are shown. Such assets are files (lectures, tasks for laboratory work), a bank of questions (a total set of questions from which tests are created to control knowledge), and grades (for laboratory work and modular control of knowledge). The goal of the work is a comparative analysis of distance learning platforms in the aspect of cybersecurity. The main threats are a violation of the availability and confidentiality of data in the educational process. It is also possible to modify marks due to the exploitation vulnerabilities of the system or gaining access to the functions of the learning content management system administrator. The probability of data being compromised is higher than the probability of modification, as evidenced by information from vulnerability databases about numerous vulnerabilities in learning content management systems. An accessibility violation is a result of a denial of service, that is, the resource on which the necessary files are located becomes inaccessible to users. The method of expert evaluation with variables of fuzzy logic is used. As a result of the analysis, it was revealed that the most flexible and convenient platform is the learning content management system of individual development, at the same time it is the most unsecure among the platforms considered. An open-source learning content management system is a more secure platform due to the presence of a global community that can identify security problems faster than attackers. Using Google Classroom and using email with cloud storage is safer, but these approaches are inferior in usability and functionality. Conclusions. Choosing a distance-learning platform is about finding a compromise between security and convenience in the form of a wide functionality of the system. When deploying a centralized learning content management system, it is important to remember that this system is an object of critical information infrastructure, and the requirements for critical systems must be met for it.

Aplikasi Penerimaan Siswa Baru (PSB) Berbasis Web Pada SDIT Yasir Cipondoh

SDIT Yasir is an Islamic elementary school located in Cipondoh, Tangerang. The Web-Based New Student Admission was created to make prospective students easier to register the school and to manage data student easily for school. Users of this application are prospective students and the registration part at SDIT Yasir. There are 5 menus available on this application, namely registration, check email, payment, payment verification and change payment data.

Comparing a Mobile Phone Automated System With a Paper and Email Data Collection System: Substudy Within a Randomized Controlled Trial.

BackgroundTraditional data collection methods using paper and email are increasingly being replaced by data collection using mobile phones, although there is limited evidence evaluating the impact of mobile phone technology as part of an automated research management system on data collection and health outcomes.ObjectiveThe aim of this study is to compare a web-based mobile phone automated system (MPAS) with a more traditional delivery and data collection system combining paper and email data collection (PEDC) in a cohort of breastfeeding women.MethodsWe conducted a substudy of a randomized controlled trial in Sydney, Australia, which included women with uncomplicated term births who intended to breastfeed. Women were recruited within 72 hours of giving birth. A quasi-randomized number of women were recruited using the PEDC system, and the remainder were recruited using the MPAS. The outcomes assessed included the effectiveness of data collection, impact on study outcomes, response rate, acceptability, and cost analysis between the MPAS and PEDC methods.ResultsWomen were recruited between April 2015 and December 2016. The analysis included 555 women: 471 using the MPAS and 84 using the PEDC. There were no differences in clinical outcomes between the 2 groups. At the end of the 8-week treatment phase, the MPAS group showed an increased response rate compared with the PEDC group (56% vs 37%; P<.001), which was also seen at the 2-, 6-, and 12-month follow-ups. At the 2-month follow-up, the MPAS participants also showed an increased rate of self-reported treatment compliance (70% vs 56%; P<.001) and a higher recommendation rate for future use (95% vs 64%; P<.001) as compared with the PEDC group. The cost analysis between the 2 groups was comparable.ConclusionsMPAS is an effective and acceptable method for improving the overall management, treatment compliance, and methodological quality of clinical research to ensure the validity and reliability of findings.

“I did not know what to expect”: Music as a means to achieving work-life balance

Work–life balance has become a buzzword in many corporate settings. This study situates itself at a higher education institute in Melbourne (Australia) where African music (singing and drumming) was used as a lever for faculty staff to “break from work” and “learn about a new music and culture”. Drawing on email communication, questionnaire data, and anecdotal feedback, a phenomenological approach was adopted to explore the benefits, challenges, and opportunities staff experienced as a recreational group music activity. Data were analyzed using interpretative phenomenological analysis as a tool. Two overarching themes emerged (group participation and learning, and challenges) and are discussed in the findings. The workshops proved successful and are worthy to be replicated in other places and spaces. Further research is needed to gain insight into whether regular music workshops can influence work–life balance and professional learning for staff.

Enhancing credit scoring with alternative data

Hundreds of millions of people in low-income economies do not have a credit or bank account because they have insufficient credit history for a credit score to be ascribed to them. In this paper we evaluate the predictive accuracy of models using alternative data, that may be used instead of credit history, to predict the credit risk of a new account. Without alternative data, the type of data that is typically available is demographic data. We show that a model that contains email usage and psychometric variables, as well as demographic variables, can give greater predictive accuracy than a model that uses demographic data only and that the predictive accuracy is sufficiently high for the demographic and email data to be used when conventional credit history data is unavailable. The same applies if merely psychometric data is included together with demographic data. However, we show that different randomly selected training: test sample splits give a wide range of predictive accuracies. In the second part of the paper, using two datasets that include only email usage as a predictor, we compare the predictive performances of a wide range of machine learning and statistical classifiers. We find that some classifiers applied to these alternative predictors give sufficiently accurate predictions for these variables to be used when no other data is available.

A feature-centric spam email detection model using diverse supervised machine learning algorithms

PurposeThis research study proposes a feature-centric spam email detection model (FSEDM) based on content, sentiment, semantic, user and spam-lexicon features set. The purpose of this study is to exploit the role of sentiment features along with other proposed features to evaluate the classification accuracy of machine learning algorithms for spam email detection.Design/methodology/approachExisting studies primarily exploits content-based feature engineering approach; however, a limited number of features is considered. In this regard, this research study proposed a feature-centric framework (FSEDM) based on existing and novel features of email data set, which are extracted after pre-processing. Afterwards, diverse supervised learning techniques are applied on the proposed features in conjunction with feature selection techniques such as information gain, gain ratio and Relief-F to rank most prominent features and classify the emails into spam or ham (not spam).FindingsAnalysis and experimental results indicated that the proposed model with sentiment analysis is competitive approach for spam email detection. Using the proposed model, deep neural network applied with sentiment features outperformed other classifiers in terms of classification accuracy up to 97.2%.Originality/valueThis research is novel in this regard that no previous research focuses on sentiment analysis in conjunction with other email features for detection of spam emails.