Email Users Research Articles

User Name Alias Extraction in Emails

Finding out user identity information from emails is one of the important research topics in email mining. Most approaches extract an email user's name only from the header of an email, but there are often many name information appearing in the body of emails, and those names are usually more suitable for representing the sender's or recipient's identity. This paper focuses on the problem of extracting email users' name aliases in the body of plain-text emails. After locating and extracting salutation and signature blocks from email bodies, we can identify the potential aliases in the salutation and signature lines, which can be directly associated with the corresponding email address in email headers, by using named entity recognition(NER) tools. However the identified aliases may be half-baked or there are still some potential aliases that can't be correctly identified. So we propose a novel approach to efficiently and accurately extract aliases in the salutation and signature lines based on name boundary word template built on the characteristics of alias neighboring words. Results on the public subset of the Enron corpus indicate that the approaches presented in this paper can efficiently extract user's aliases from email bodies.

Designing an E-Mail Prototype to Enhance Effective Communication and Task Management: A Case Study

This paper deals with communicational breakdowns and misunderstandings in computer mediated communication (CMC) and ways to recover from them or to prevent them. The paper describes a case study of CMC conducted in a company named Artigiani. We observed communication and conducted content analysis of e-mail messages, focusing on message exchanges between customer service representatives (CSRs) and their contacts. In addition to task management difficulties, we identified communication breakdowns that result from differences between perspectives, and from the lack of contextual information, mainly technical background and professional jargon at the customers’ side. We examined possible ways to enhance CMC and accordingly designed a prototype for an e-mail user interface that emphasizes a communicational strategy called contextualization as a central component for obtaining effective communication and for supporting effective management and control of organizational activities, especially handling orders, price quoting, and monitoring the supply and installation of products.

Using insights from email users to inform organisational email management policy

One would expect email substantially to increase organisational productivity and efficiency. There is little empirical evidence of this since email use is such a complex tool that it would be well nigh impossible to attribute efficiency increases solely to email. There is anecdotal evidence of the positive aspects of email (Phillips, S.R. and Eisenberg, E.M., 1996. Strategic uses of electronic mail in organisations. The Public, 3 (4), 67–81; Virji, A., et al., 2006. Use of email in a family practice setting: opportunities and challenges in patient- and physician-initiated communication. BMC Medicine, 4 (18), doi: 10.1186/1741-7015-4-18), and of aspects of email usage that cause aggravation and concern (Whittaker, S. and Sidner, C., 1996. Email overload: exploring personal information. Management of email. In: Proceedings of the ACM conference on human factors in computer systems, Atlanta, Georgia, USA. New York: ACM, 276283; Fischer, D., et al., 2006. Revisiting Whittaker and Sidner's “email overload” ten years later. In: Proceedings of the 2006 20th anniversary conference on computer supported cooperative work, 4–8 November 2006 Banff, Alberta, Canada. New York: ACM, 309–312). Such anecdotal evidence is of limited use in assessing efficiency gains but serves to prompt studies into the impact of the pervasiveness of organisational email on individual employees. To study this, we spoke to email users about their experiences through a series of reflective semi-structured interviews to gauge the effects of email on the individual user. We linked our findings to a number of behavioural principles and assessed whether the identified email-related behaviours should be encouraged, forbidden or modified. We propose one way of addressing unhelpful emailing behaviours to maximise email's potential for enhancing productivity. We argue that such insights from the level of the individual emailer are the key to maximising email's potential to fulfil its original purpose as a productivity enhancer.

Family and work-related consequences of addiction to organizational pervasive technologies

While organizational pervasive technologies, such as mobile computing, can contribute to increased productivity, their nature can also result in technology addiction. We applied the behavior–environment interface of social cognitive theory to explain several negative familial and organizational consequences of addiction to work-related pervasive technologies. Our empirical study of 241 organizational mobile email users revealed that their levels of addiction to mobile email increased their perceived work overload and technology–family conflict. Perceived work overload, in turn, reduced their organizational commitment. Furthermore, elevated levels of perceived work overload together with augmented technology–family conflict fostered work–family conflict. Implications for research and practice are suggested.

Ethical dimensions of spam

The explosion of spam within the world's e-mail system has seriously impaired the usefulness of e-mail as a reliable and trustworthy medium for interpersonal communication. Spam raises important societal concerns that are potentially corrosive in their impact. This paper considers the origins of spam and describes in some detail spam's application and content. In addition, this paper explores the role that spam filtering and blocking plays in the administration of e-mail services. The ultimate objective of this paper is to apply the ethical framework developed by Berenheim (1988) to better understand the impact that spam has on e-mail users and to examine the ethical issues connected with the distribution and regulation of spam.

The Gender Digital Divide in the Research Sectors of Ghana, Kenya, and Kerala

This article uses panel data gathered in 2001 and 2005 to assess the gendered digital divide among researchers employed in three developing countries: Ghana, Kenya, and India (the state of Kerala). We move the digital divide discussion from an early focus on differentials in adoption and access to an assessment of use as measured by the diversity and intensity of Internet and e-mail activity. Using both bivariate and multivariate analyses, our results indicate clear gender disparities within an increasingly technologically saturated environment. Over time, both women and men report significant increases in access to and use of various technologies, yet even after controlling for other factors, women continue to be less technologically oriented than their male counterparts. Although women adopt new technologies around the same time and display similar patterns of e-mail use as men, they are less intense users of both e-mail and the Web, and they use the Web less diversely than men. We conclude by suggesting possibilities for future research and significant policy implications for the assessment of the digital divide in low-income areas.

Information and communication technology adoption and diffusion in micro-enterprises: the case of techno-savvy home-based businesses

The effective use of ICTs for business activities is of significant interest in a digital economy. This paper examines the adoption and diffusion of ICTs by micro home-based businesses (HBB) from an empirical study of 522 firms. Key findings include very high levels of internet, e-mail and cell phone usage for HBBs’ business activities; and increasing website adoption levels with increasing geographic sales reach (from local, regional, national, to international). In spite of micro size and limited resources, many of these HBB were techno-savvy and capable of utilising the full range of ICTs to facilitate electronic business communications and online transactions. These findings are significant given the lack of prior research on the HBB sector and the scale of micro-enterprises in economies around the globe.

A Trial for the Management of Email Delivery Delay Problem Associated with Spam Mails Filtering in University

Spam mail management in universities differs from that in enterprises having uniform and strict network policy, and requires the guarantee of a free policy of mail environment. In this paper, we report on the findings from the operation experiment of adopted spam mail filtering based on the volunteer application of users to the management. In particular, management of the electronic mail (email) delivery delay problem is picked up under the consideration of the state of the email usage in our university. We also discuss an ideal method of the spam mail filtering in universities and in research institutes under the free policy of mail environment.

Clusters, recipients and reciprocity: Extracting more value from email communication networks

A common problem in the empirical research of communication networks is how to construct network models from raw data. Email communication datasets are typically transformed into networks in which nodes designate email users and ties connect nodes if an email has been exchanged between the corresponding users. Unfortunately, this method of extracting sender-recipient dyads from multiple recipient emails conceals information regarding the nature of affiliations and the process by which they come about. Specifically, the findings of this paper indicate that recipient lists of a user's outgoing emails are not arbitrary subsets of the user's contacts. Instead, recipient lists delineate meaningful organizational units so that being co-recipients of the same email(s) is a stronger indication of affiliation than being neighbors of the same node(s). Moreover, the number of recipients in an email reveals not only the nature of affiliations within the network but also the way in which these relationships are likely to unfold. Methodologically, this paper engages in a search for new ways to construct network models that extract more value from existing data. Theoretically, the findings could inform the debate between interaction approaches and network sciences.

Using Text Messaging in an Undergraduate Nursing Course

Text messaging is a popular means of communication among young adults. Consequently, this mode of communication may be used to positively influence students in their academic studies. In this study, students were given the opportunity to receive text or e-mail messages regarding lecture content. Short message reminders, in the form of texts or e-mails, were used to send bite-sized course content to undergraduate nursing students. Messages included questions that would be answered in the next day's lecture or reiterated a main point presented in the previous day's lecture. Following a survey at the end of the course, text users responded positively toward this pedagogical approach and felt the use of text messaging enhanced their learning experience. E-mail users reported a short message reminder was moderately useful to their study of anatomy. These results suggest text messaging may be a valuable tool for educators as they seek to incorporate technology into the classroom.

Analyzing Internet e-mail date-spoofing

Spammers and phishers constantly keep on changing spam structure to circumvent anti-spam procedures and target maximum recipients. Of late, it has been observed that spammers spoof date header of their spam e-mails to keep them on top in the recipient’s mailbox with an aim to maximize the chances of immediate attention of recipients. This form of spoofing can cause confusion to recipients, create problems in time bound transactions, increase chances of opening spam, worsen the problem of false positive, result in loss of work productivity, render date header field insignificant and would spawn a host of legal issues. This paper reports date-spoofing, analyzes implications of date-spoofed e-mails on some commercial and corporate e-mail servers and surveys e-mail user behavior. It further discusses detection of date-spoofed e-mails to enable forensic examinations of date forged e-mails and presents possible technical solutions to stop date-spoofing.

A Study on Email Spam Filtering Techniques

Electronic mail is used daily by millions of people to communicate around the globe and is a mission-critical application for many businesses. Over the last decade, unsolicited bulk email has become a major problem for email users. An overwhelming amount of spam is flowing into users‟ mailboxes daily. Not only is spam frustrating for most email users, it strains the IT infrastructure of organizations and costs businesses billions of dollars in lost productivity. The necessity of effective spam filters increases. In this paper, we presented our study on various problems associated with spam and spam filtering methods, techniques. General Terms Spam, spam filtering

Openings and closings in Spanish email conversations

Despite the increasing interest scholarly research has shown in the study of computer-mediated communication, there is still a need to investigate the empirical validity of assumed homogeneity of language usage over the net and focus on the social diversity and variation that characterizes any communication. With this in mind, the present paper is an investigation into the stylistic choices that a particular group of email users made when engaged in a specific activity type. More specifically, it explores the variation in the discourse practices employed to open and close emails in conversation alongside the institutional power of participants and the interactional position of each email contributing to the conversation. To carry out this study a corpus of short email conversations in Peninsular Spanish was collected ( n = 240). The analysis focused on the opening and closing sequences of the emails that made up the conversations and considered opening and closing linguistic conventions as discursive practices that members of a community may use strategically. The findings revealed that the discursive practices under scrutiny were subject not only to technological but also to social and interactional constraints and thus highlighted contextual variability. Further, the high degree of sociability in the electronic episodes studied was interpreted as reflecting a “people first, business second” communicative style.

Machine Learning Email Prediction System (MLEPS)

Nowadays, email has become one of the most critical personal and business applications and email users would experience serious consequences if email messages could not be available or experience high volume of messages which lead to congestions, overloads and limited storage space coupled with unstructured messages in mail boxes. A few years ago, the means of communication are via letters by post, telegraph, fax, couriers to mention a few but now the focus has changed to a faster means of obtaining quick responses and faster ways of communication-emails. We propose a new framework to help organise and prioritize email better; Machine learning email prediction system (MLEPS). The goal is to organise emails better in mail boxes, prioritise emails based on the focus of the email content. The intelligent email prediction system helps to improve email users’ performances, saves time, very effective and efficient tool and is cost effective for businesses and for personal use. The system is evaluated against a corpus of human-judged predictions, reaching satisfactory level of performance.

Automatic E-mail Classification Using Dynamic Category Hierarchy and Semantic Features

The explosive increase in the use of e-mails has produced a large amount of information, and caused a problem in that many spam or regular e-mails with the same or similar contents are duplicated over and over day-to-day. We often group e-mails into categories in order to maintain e-mails efficiently. However, reading the e-mail messages and classifying them is still a tedious task. Moreover, the number of e-mails and its manual classification is increasing every day. So, e-mail users are demanding methods that can classify e-mails more and more efficiently. In this paper, we propose an e-mail multicategory classification and e-mail message reorganization method using semantic features and a dynamic category hierarchy reconstruction method. The proposed method in this paper classifies multicategory e-mails automatically and supports keyword and directory search methods in the classified results so that a large volume of e-mails can be managed efficiently. In addition, we used an interactive dynamic category hierarchy reconstruction method in which the user reorganizes all e-mail messages into categories and thus enhances the efficiency of directory searches.

In the News

Recent experimental AI-enhanced applications focus on putting the user in control of human-computer interface systems. Examples include microsearch engines, which use reasoning techniques such as probabilistic inference, deterministic inference, optimization, estimation, and configuration to fine tune their results, and an Australian intelligent grid system that lets homeowners decide how to optimize their energy use. Researchers are also exploring utilizing user input to help email users separate junk from important communications and investigating more interactive videogame nonplayer characters. Other AI apps in the works include intelligent transportation systems and applying AI methodologies to sports analysis.

인터넷 포털사이트 서비스의 지속적 이용의도에 영향을 미치는 요인에 관한 연구

Portal sites have been providing diverse services to attract new users and retain existing customers. Recently, they also added new services and increased quality of the services they provide to secure more customers. It is, however, not clear how people actually react to such activities. We wanted to understand the mechanism associated with users` continued usage intention of current Portal site. We assumed search, e-mail, information, community, e-commerce services as key services provided by most Portal sites and considered valuable by many customers. The quality of these services may directly affect users` continued usage intention. However, we can also assume that attractive alternatives and switching cost may have some influence on users` continued usage intention. Therefore, in this study, key variables pertaining to the quality of key services provided by Portal sites, attractive alternatives, and switching cost were examined to explain the dynamics of users` continued usage intention. An empirical study based on 891 survey responses showed the importance of the quality of key services for users` continued usage intention. Switching cost also demonstrated strong association with users` continued usage intention. However, attractive alternatives did not show a significant association with users` continued usage intention. We also found that the variable attractive alternatives moderated the relationship between the quality of search service and users` continued usage intention and the relationship between the quality of information service and users` continued usage intention. On the other hand, the variable switching cost showed a moderating effect on the relationship between the quality of e-mail service and users` continued usage intention and the relationship between the quality of community service and users` continued usage intention. This study implies that Portal sites need to make efforts not only to improve the quality of key services but also to consider attractiveness of other Portal sites` services and switching cost to secure more customers.

A web-based model for simulating whole-farm beef cattle systems

This paper details the rationale and procedures included in a web-based simulator containing production of beef cattle and cash crops. All biophysical and economical definitions including management in terms of rules constitute user-defined scenarios, which can be saved, retrieved, modified and deleted. Herbage growth may be either provided by the user or estimated from daily climate information. Scenarios are simulated and their outcomes are sent to the user's e-mail as a spreadsheet file, including data and pre-designed graphs to facilitate the interpretation of results. An example simulation study of a grazing-based finishing beef steers with a cycle of 12 months is presented, where new weaners enter the system in the autumn. Increased stocking rates, SR (150, 170, 190 and 210 heads in a 100-ha farm) and different summer maize feeding (SMF) rates were compared (SMF 0 = control and SMF 1 = intermittent rule-driven maize feeding during summer). In this simulation study, “deviations” from user-defined targets are simplified into two associated rules (a) average farm herbage mass deviation to adjust herbage allowance, and (b) target animal live weight deviation, associated to SMF 1. The proportion of unfinished steers at 28th February increased linearly ( p ≤ 0.01) with higher stocking rates and became zero at any stocking rate where the SMF rule was operating (SMF 1). The economic response of SR × SMF interaction was significant for gross margin, indicating a positive linear association ( p ≤ 0.05) of SMF 1 treatment (rule activated) when SR increases. The potential use of the web simulator as a flexible tool for investigation, training and decision making are discussed.

Launching Email Spoofing Attacks

To launch a spoofing attack with emails we need to have knowledge of the techniques to launch an email spoofing attack. Spoofing has been widely discussed in documents on the Internet. Email spoofing is termed as an attack on email users who are sent emails from email addresses that are fake or altered. An attacker may pose as other legitimate user to fool or cheat an user.

Improving the performance of Naive Bayes multinomial in e-mail foldering by introducing distribution-based balance of datasets

E-mail foldering or e-mail classification into user predefined folders can be viewed as a text classification/categorization problem. However, it has some intrinsic properties that make it more difficult to deal with, mainly the large cardinality of the class variable (i.e. the number of folders), the different number of e-mails per class state and the fact that this is a dynamic problem, in the sense that e-mails arrive in our mail-folders following a time-line. Perhaps because of these problems, standard text-oriented classifiers such as Naive Bayes Multinomial do no obtain a good accuracy when applied to e-mail corpora. In this paper, we identify the imbalance among classes/folders as the main problem, and propose a new method based on learning and sampling probability distributions. Our experiments over a standard corpus (ENRON) with seven datasets (e-mail users) show that the results obtained by Naive Bayes Multinomial significantly improve when applying the balancing algorithm first. For the sake of completeness in our experimental study we also compare this with another standard balancing method (SMOTE) and classifiers.