The classifier discussed in this thesis considers the path traversed by an email (instead of its content) and reputation of the relays, features inaccessible to spammers. Groups of spammers and individual behaviors of a spammer in a given domain were analyzed to yield association patterns, which were then used to identify similar spammers. Unsolicited and phishing emails were successfully isolated from legitimate emails, using analysis results. Spammers and phishers are also categorized into serial spammers/phishers, recent spammers/phishers, prospective spammers/phishers, and suspects. Legitimate emails and trusted domains are classified into socially close (family members, friends), socially distinct (strangers etc), and opt-outs (resolved false positives and false negatives). Overall this classifier resulted in far less false positives when compared to current filters like SpamAssassin, achieving a 98.65% precision, which is well comparable to the precisions achieved by SPF, DNSRBL blacklists.

With the amount of email spam received these days it is hard to imagine that spammers act individually. Nowadays, most of the spam emails have been sent from a collection of compromised machines controlled by some spammers. These compromised computers are often called bots, using which the spammers can send massive volume of spam within a short period of time. The motivation of this work is to understand and analyze the behavior of spammers through a large collection of spam mails. My research examined a the data set collected over a 2.5-year period and developed an algorithm which would give the botnet features and then classify them into various groups. Principal component analysis was used to study the association patterns of group of spammers and the individual behavior of a spammer in a given domain. This is based on the features which capture maximum variance of information we have clustered. Presence information is a growing tool towards more efficient communication and providing new services and features within a business setting and much more. The main contribution in my thesis is to propose the willingness estimator that can estimate the callee's willingness without his/her involvement, the model estimates willingness level based on call history. Finally, the accuracy of the proposed willingness estimator is validated with the actual call logs.

The present study was conducted to explore the effectiveness of a worksite stress management program delivered via electronic mail (e-mail). One hundred and thirty-seven employed adults (36 males, 102 females; mean age = 29.46) from several diverse businesses consented to participate. The volunteers completed Cohen's Perceived Stress Scale, the Daily Hassles Scale, the Daily Work Hassles Scale, the TCU Self-Ratings Scales, and a demographic and opinion questionnaire. Individuals in the treatment group received e-mail messages twice weekly and had access to a website for three months about a variety of cognitive-behavioral techniques for managing worksite stress. A MANCOVA of post-intervention stress levels indicated that individuals who received the stress management messages perceived the same amount of stressors and hassles as individuals who did not receive the messages [F (5, 86) = 0.95, p = .45]. However, a MANCOVA of post-intervention perceived mood states revealed a tendency for individuals in the treatment group to be less depressed, anxious, and angry than individuals in the control group [F (3, 92) = 2.44, p = .07]. Demographic variables did not influence the outcome variables and pre- and post-test absenteeism and illness rates were similar for treatment and control groups. Coping skill usage was similar in amount and frequency, but differed in quality between the groups. The findings of the present study indicate that health promotion programs can be feasibly and effectively delivered via e-mail in the worksite.

The motivation of this work is to understand E-shape analysis and how it can be applied to various classification tasks. It has a powerful feature to not only look at what information is contained, but rather how that information looks. This new technique gives E-shape analysis the ability to be language independent and to some extent size independent. In this thesis, I present a new mechanism to characterize an email without using content or context called E-shape analysis for email. I explore the applications of the email shape by carrying out a case study; botnet detection and two possible applications: spam filtering and social-context based finger printing. The second part of this thesis takes what I apply E-shape analysis to activity recognition of humans. Using the Android platform and a T-Mobile G1 phone I collect data from the triaxial accelerometer and use it to classify the motion behavior of a subject.

published_or_final_version / Business Administration / Master / Master of Business Administration

No description available.

No description available.

A research report submitted to the Faculty of Humanities, School of Human and Community Development, in partial fulfilment of the requirements for the degree of Master of Arts by coursework and research report in the field of in Organisational Psychology, University of the Witwatersrand, Johannesburg September 2017 / Emails have become a fundamental computer application and business tool, in organisations across the global. This is because of the accessibility and convenience of emails which have generated an array of benefits to both employees and their organisations. However, this accessibility has led to an over-reliance on emails, which often has the negative consequence of email overload. Email overload continues to be a recurring issues experienced by employees universally, which research has found to have negative implications on employees’ wellbeing and productivity. Yet there has been limited research, particularly in South Africa, that aims to reduce email overload among employees. Thus, this research report investigated how the role of providing employees with a job resource (training intervention) could increase perceived productivity and eliminate email overload and change caused by the job demands (emails) on employees .In order to examine this effect, this research utilised a pretest post-test control group design on order to compare the impact of a training intervention in reducing email overload and increasing productivity. The quantitative results revealed that the training intervention contributed to a decrease in feelings of email overload among the participants. Additionally, focus groups were administered to determine participants’ experience with emails both prior to the training and after the training, to gain a clearer understanding of the best practices used to eliminate email overload. These findings observed that the participants transferred learnt contents from training into their working lives. Thus research both further contributes to other research currently associated with email and email overload, and also provides a greater understanding of the need to provide employees with job resources much like training intervention in order to counteract those job demands like emails, that are often ignored. / XL2018

Typescript (photocopy). / Digitized by Kansas Correctional Industries

Electronic mail has become a widely used medium of communication in academia, government, and business. It is unique as a communication medium because it makes conversations across time, space, and organizational levels possible. The ability of electronic mail to "forward" a message allows for the creation of chains that preserve the entire conversation for each participant. This appears to be a new linguistic form in which the interactive features of spoken conversation are realized using electronically transmitted text. The purpose of the present study was to determine the extent of the similarities and differences between spoken conversation and electronic mail exchanges. The research questions addressed were 1) What techniques that occur in spoken conversations also occur in electronic mail exchanges?, and 2) How are the techniques used in spoken conversations modified or different in electronic mail exchanges? The data used in this study consisted of electronic mail text collected by the author in the course of her daily work in the data processing division of a large financial institution. The authors were computer technicians and middle managers with a wide diversity of educational backgrounds. Sixteen samples of message "chains" that contained at least three individual messages were selected for in-depth analysis. These samples were analyzed for conversational openings and closings, tum-taking mechanisms, adjacency pairs, and repetition. Of the structural features studied, repetition was used in ways most similar to its uses in spoken conversation. The feature having the most differences from spoken interaction was the tum-taking system. In the electronic mail exchanges there was more variation in the sender's selection of the next sender, including the option for multiple simultaneous replies. Openings and closings took many forms, some of them the same as in spoken conversation. Among the forms that differed were openings that resembled the salutation in a letter and closings that followed each individual message in a "chain." Adjacency pairs such as questions and closings were paired as in spoken conversation, while openings, thanks, and apologies occurred as single utterances.