Search results

SIMPR (Structured Information Management: Processing and Retrieval) is an ESPRIT II Project aiming to achieve technological advances in information management This new technology is instantiated in the SIMPR software system. SIMPR will process documents by indexing them and classifying their subjects, before storing them in an electronic information base from which they can then be retrieved using simple natural language search requests. Building this system has required initiatives in automatic indexing, in language analysis, in subject classification and in machine learning. These initiatives are discussed in this paper, in the context of the strategy and achievements to date of the SIMPR Project.

Distinguishing phishing emails from legitimate emails continues to be a difficult task for most individuals. This study aims to investigate the psycholinguistic factors associated with deception in phishing email text and their effect on end-user ability to discriminate phishing emails from legitimate emails.

Email messages and end-user decisions collected from a laboratory phishing study were validated and analyzed using natural language processing methods (Linguistic Inquiry Word Count) and penalized regression models (LASSO and Elastic Net) to determine the linguistic dimensions that attackers may use in phishing emails to deceive end-users and measure the impact of such choices on end-user susceptibility to phishing.

We found that most participants, who played the role of a phisher in the study, chose to deceive their end-user targets by pretending to be a familiar individual and presenting time pressure or deadlines. Results show that use of words conveying certainty (e.g. always, never) and work-related features in the phishing messages predicted higher end-user vulnerability. On the contrary, use of words that convey achievement (e.g. earn, win) or reward (cash, money) in the phishing messages predicted lower end-user vulnerability because such features are usually observed in scam-like messages.

Insights from this research show that analyzing emails for psycholinguistic features associated with computer-mediated deception could be used to fine-tune and improve spam and phishing detection technologies. This research also informs the kinds of phishing attacks that must be prioritized in antiphishing training programs.

Applying natural language processing and statistical modeling methods to analyze results from a laboratory phishing experiment to understand deception from both attacker and end-user is novel. Furthermore, results from this work advance our understanding of the linguistic factors associated with deception in phishing email text and its impact on end-user susceptibility.

The purpose of this article is to present an aggregated methodology for construction of the stop word list in Farsi language and generate a generic Farsi stop word list.

The stop word list is extracted based on: syntactic classes, domain dependent, corpus statistic and expert judgments. Some of the main challenges that arise in the Farsi automatic text processing are outlined as well.

Results from the techniques are aggregated and a general Farsi stop word list containing 927 words is generated.

The created stop word list can affect the efficiency and effectiveness of retrieval and indexing process in Farsi information retrieval system, moreover, it can play an important role during Farsi text segmentation.

Our stop word extraction algorithm is a promising technique; it could be applied into other languages that they have ambiguities in automatic text segmentation.

This paper aims to present an evaluation of open source OCR for supporting research on material in small‐ to medium‐scale historical archives.

The approach was to develop a workflow engine to support the easy customisation of the OCR process towards the historical materials using open source technologies. Commercial OCR often fails to deliver sufficient results here, as their processing is optimised towards large‐scale commercially relevant collections. The approach presented here allows users to combine the most effective parts of different OCR tools.

The authors demonstrate their application and its flexibility and present two case studies, which demonstrate how OCR can be embedded into wider digitally enabled historical research. The first case study produces high‐quality research‐oriented digitisation outputs, utilizing services that the authors developed to allow for the direct linkage of digitisation image and OCR output. The second case study demonstrates what becomes possible if OCR can be customised directly within a larger research infrastructure for history. In such a scenario, further semantics can be added easily to the workflow, enhancing the research browse experience significantly.

There has been little work on the use of open source OCR technologies for historical research. This paper demonstrates that the authors' workflow approach allows users to combine commercial engines' ability to read a wider range of character sets with the flexibility of open source tools in terms of customisable pre‐processing and layout analysis. All this can be done without the need to develop dedicated code.

Office work has grown explosively in this century. Once a small occupational category, office work now includes about 40 percent of the American work force. Yet office work continues to be “the familiar unknown”: we worry about its growing size, we are concerned about its productivity, and we design systems to improve it; but our real knowledge of what goes on in the office is very shallow. This article discusses only a few of the many subtle facets of office work that vendors and users must understand to meet the needs of this attractive, but difficult market.

New methods are needed for accessing very large information services. This paper proposes the use of a user model neural network to allow better access to a news service. The network is constructed on the basis of articles read, and articles marked as rejected. It adapts over time to better represent the user's interests and rank the articles supplied by the news service. Using an augmented keyword search we can also search for articles using keywords in conjunction with the user model neural network. Trials of the system in a USENET news environment show promising results for the use of this approach in information retrieval.

Smart card-based E-payment systems are receiving increasing attention as the number of implementations is witnessed on the rise globally. Understanding of user adoption behavior of E-payment systems that employ smart card technology becomes a research area that is of particular value and interest to both IS researchers and professionals. However, research interest focuses mostly on why a smart card-based E-payment system results in a failure or how the system could have grown into a success. This signals the fact that researchers have not had much opportunity to critically review a smart card-based E-payment system that has gained wide support and overcome the hurdle of critical mass adoption. The Octopus in Hong Kong has provided a rare opportunity for investigating smart card-based E-payment system because of its unprecedented success. This research seeks to thoroughly analyze the Octopus from technology adoption behavior perspectives.

Cultural impacts on adoption behavior are one of the key areas that this research posits to investigate. Since the present research is conducted in Hong Kong where a majority of population is Chinese ethnicity and yet is westernized in a number of aspects, assuming that users in Hong Kong are characterized by eastern or western culture is less useful. Explicit cultural characteristics at individual level are tapped into here instead of applying generalization of cultural beliefs to users to more accurately reflect cultural bias. In this vein, the technology acceptance model (TAM) is adapted, extended, and tested for its applicability cross-culturally in Hong Kong on the Octopus. Four cultural dimensions developed by Hofstede are included in this study, namely uncertainty avoidance, masculinity, individualism, and Confucian Dynamism (long-term orientation), to explore their influence on usage behavior through the mediation of perceived usefulness.

TAM is also integrated with the innovation diffusion theory (IDT) to borrow two constructs in relation to innovative characteristics, namely relative advantage and compatibility, in order to enhance the explanatory power of the proposed research model. Besides, the normative accountability of the research model is strengthened by embracing two social influences, namely subjective norm and image. As the last antecedent to perceived usefulness, prior experience serves to bring in the time variation factor to allow level of prior experience to exert both direct and moderating effects on perceived usefulness.

The resulting research model is analyzed by partial least squares (PLS)-based Structural Equation Modeling (SEM) approach. The research findings reveal that all cultural dimensions demonstrate direct effect on perceived usefulness though the influence of uncertainty avoidance is found marginally significant. Other constructs on innovative characteristics and social influences are validated to be significant as hypothesized. Prior experience does indeed significantly moderate the two influences that perceived usefulness receives from relative advantage and compatibility, respectively. The research model has demonstrated convincing explanatory power and so may be employed for further studies in other contexts. In particular, cultural effects play a key role in contributing to the uniqueness of the model, enabling it to be an effective tool to help critically understand increasingly internationalized IS system development and implementation efforts. This research also suggests several practical implications in view of the findings that could better inform managerial decisions for designing, implementing, or promoting smart card-based E-payment system.

Two valuable pieces of information – reviews and their corresponding numerical ratings – are accessible to potential customers before they make a purchasing decision. An extensive body of marketing literature has scrutinized the influence of customers’ reviews by linking such aspects as the volume and valance of reviews with product sales and customers’ purchase intention. The aim of this study, for which dual coding theory was used, was to understand the relationship between reviews and their corresponding numerical ratings.

The authors used the latent Dirichlet allocation technique to categorize customers’ reviews. The present findings contribute to the literature by showing the underlying mechanisms that customers use to interpret reviews and associate them with numerical ratings.

The gradient boosted decision tree model demonstrates that non-abstract-dominant reviews (reviews mainly consist of tangible objects, actions, events or affective words) are significant predictors of their corresponding numerical ratings. However, abstract-dominant reviews (i.e. those consisting primarily of intangible objects, events or actions) cannot predict their associated numerical ratings.

The present findings contribute to the literature by showing the underlying mechanisms that customers use to interpret reviews and associate them with numerical ratings.

Consideration can be defined as the process of giving careful thought to something. When an IEP team considers the instructional programming and related goals and objectives for a student identified eligible for special education services, the process gives careful attention to a multitude of factors from different perspectives that result in individualized instruction for that student. Similarly, when assistive technology is considered for students with certain learning characteristics, careful attention must be given to ensure that the recommended assistive technology is required for the student to be successful and reflects an appropriate match between him/her and the tools (Zabala, 1995, 1996). For example, given that prescription eyeglasses can be considered assistive technology, and that a certain degree of visual acuity is generally needed in order for an individual to visually access print, one can see the importance of ensuring that the prescription is indeed required for an individual to perform and is appropriately matched to the visual needs of the individual. If eyeglasses are arbitrarily assigned to an individual, they may serve as an obstacle for the individual to see properly, thus, hampering his/her overall performance.

The age of technology is here, bringing to our working lives new phrases such as “the automated office”, “the electronic office” or “the office of the future” in which we work systems that are “ergonomically designed” or “user friendly”—to name but a few examples of eighties' buzz words.