Text mining and probabilistic language modeling for online review spam detecting

In the era of Web 2.0, huge volumes of consumer reviews are posted to the Internet every day. Manual approaches to detecting and analyzing fake reviews (i.e., spam) are not practical due to the problem of information overload. However, the design and development of automated methods of detecting fake reviews is a challenging research problem. The main reason is that fake reviews are specifically composed to mislead readers, so they may appear the same as legitimate reviews (i.e., ham). As a result, discriminatory features that would enable individual reviews to be classified as spam or ham may not be available. Guided by the design science research methodology, the main contribution of this study is the design and instantiation of novel computational models for detecting fake reviews. In particular, a novel text mining model is developed and integrated into a semantic language model for the detection of untruthful reviews. The models are then evaluated based on a real-world dataset collected from amazon.com. The results of our experiments confirm that the proposed models outperform other well-known baseline models in detecting fake reviews. To the best of our knowledge, the work discussed in this article represents the first successful attempt to apply text mining methods and semantic language models to the detection of fake consumer reviews. A managerial implication of our research is that firms can apply our design artifacts to monitor online consumer reviews to develop effective marketing or product design strategies based on genuine consumer feedback posted to the Internet.

Mining a data reasoning model for personalized text classification

It is a big challenge to acquire correct user profiles for personalized text classification since users may be unsure in providing their interests. Traditional approaches to user profiling adopt machine learning (ML) to automatically discover classification knowledge from explicit user feedback in describing personal interests. However, the accuracy of ML-based methods cannot be significantly improved in many cases due to the term independence assumption and uncertainties associated with them. This paper presents a novel relevance feedback approach for personalized text classification. It basically applies data mining to discover knowledge from relevant and non-relevant text and constraints specific knowledge by reasoning rules to eliminate some conflicting information. We also developed a Dempster-Shafer (DS) approach as the means to utilise the specific knowledge to build high-quality data models for classification. The experimental results conducted on Reuters Corpus Volume 1 and TREC topics support that the proposed technique achieves encouraging performance in comparing with the state-of-the-art relevance feedback models.

Effective health communication in the mining industry

Historically, occupational health and safety has primarily presented as attempts to create a safer work environment for employees. The mining industry carries health and safety risks, often greater than other occupations. Whilst the mining industry is regulated by stringent workplace health and safety regulations, the very nature of the work and environmental influences expose employees to a greater number of injury risk factors than many other industries. The application of risk management techniques has resulted in a substantial decline in injury rates observed for mining operations in developed countries (Donoghue, 2004). This essential focus can be complemented by a more comprehensive approach to occupational health and safety that also supports the design and delivery of proactive health promotion programs...

Finding and matching communities in social networks using data mining

The rapid growth in the number of users using social networks and the information that a social network requires about their users make the traditional matching systems insufficiently adept at matching users within social networks. This paper introduces the use of clustering to form communities of users and, then, uses these communities to generate matches. Forming communities within a social network helps to reduce the number of users that the matching system needs to consider, and helps to overcome other problems from which social networks suffer, such as the absence of user activities' information about a new user. The proposed system has been evaluated on a dataset obtained from an online dating website. Empirical analysis shows that accuracy of the matching process is increased using the community information.

Discovering novel knowledge using granule mining

This paper presents an extended granule mining based methodology, to effectively describe the relationships between granules not only by traditional support and confidence, but by diversity and condition diversity as well. Diversity measures how diverse of a granule associated with the other granules, it provides a kind of novel knowledge in databases. We also provide an algorithm to implement the proposed methodology. The experiments conducted to characterize a real network traffic data collection show that the proposed concepts and algorithm are promising.

Corporate, risk, mining camps and knowledge/power

Australia is currently in the midst of a major resources boom. However the benefits from the boom are unevenly distributed, with state governments collecting billions in royalties, and mining companies billions in profits. The costs are borne mostly at a local level by regional communities on the frontier of the mining boom, surrounded by thousands of men housed in work camps. The escalating reliance on non–resident workers housed in camps carries significant risks for individual workers, host communities and the provision of human services and infrastructure. These include rising rates of fatigue–related death and injuries, rising levels of alcohol–fuelled violence, illegally erected and unregulated work camps, soaring housing costs and other costs of living, and stretched basic infrastructure undermining the sustainability of these towns. But these costs have generally escaped industry, government and academic scrutiny. This chapter directs a critical gaze at the hopelessly compromised industry–funded research vital to legitimating the resource sector’s self–serving knowledge claims that it is committed to social sustainability and corporate responsibility. The chapter divides into two parts. The first argues that post–industrial mining regimes mask and privatise these harms and risks, shifting them on to workers, families and communities. The second part links the privatisation of these risks with the political economy of privatised knowledge embedded in the approvals process for major resource sector projects.

Established-outsider relations and fear of crime in mining towns

Using Elias and Scotson's (1994) account of established-outsider relations, this article examines how the organisational capacity of specific social groups is significant in determining the quality of crime-talk in isolated and rural settings. In particular, social 'oldness' and notions of what constitutes 'community' are significant in determining what activities and individuals are salient within crime-talk. Individual and gorup interviews, conducted in a West Australian mining town, revealed how crime-talk is an artefact of specific social figurations and the relative ability of groups to act as cohesive and integrated networks. We argue that anxieties regarding crime are a product of specific social figurations and the shifting power ratios of groups within such figurations.

Environmental reporting in the Australian mining industry : complying with regulation or meeting international best practice?

It is nearly 10 years since the introduction of s 299(1)(f) Corporations Act , which requires the disclosure of information regarding a company's environmental performance within its annual report. This provision has generated considerable debate in the years since its introduction, fundamentally between proponents of either a voluntary or mandatory environmental reporting framework. This study examines the adequacy of the current regulatory framework. The environmental reporting practices of 24 listed companies in the resources industries are assessed relative to a standard set by the Global Reporting Initiative (GRI) Sustainability Reporting Guidelines. These Guidelines are argued to represent "international best practice" in environmental reporting and a "scorecard" approach is used to score the quality of disclosure according to this voluntary benchmark. Larger companies in the sample tend to report environmental information over and above the level required by legislation. Some, but not all companies present a stand-alone environmental/sustainability report. However, smaller companies provide minimal information in compliance with s 299(1)(f) . The findings indicate that "international best practice" environmental reporting is unlikely to be achieved by Australian companies under the current regulatory framework. In the current regulatory environment that scrutinises s 299(1)(f) , this article provides some preliminary evidence of the quality of disclosures generated in the Australian market.

Mining work, family and community : a spatially-oriented approach to the impact of the Ravensthorpe nickel mine closure in remote Australia

While changes in work and employment practices in the mining sector have been profound, the literature addressing mining work is somewhat partial as it focuses primarily on the workplace as the key (or only) site of analysis, leaving the relationship between mining work and families and communities under-theorized. This article adopts a spatially oriented, case-study approach to the sudden closure of the Ravensthorpe nickel mine in the south-west of Western Australia to explore the interplay between the new scales and mobilities of labour and capital and work–family–community connections in mining. In the context of the dramatically reconfigured industrial arena of mining work, the study contributes to a theoretical engagement between employment relations and the spatial dimensions of family and community in resource-affected communities.

Text mining in negative relevance feedback

It is a big challenge to clearly identify the boundary between positive and negative streams. Several attempts have used negative feedback to solve this challenge; however, there are two issues for using negative relevance feedback to improve the effectiveness of information filtering. The first one is how to select constructive negative samples in order to reduce the space of negative documents. The second issue is how to decide noisy extracted features that should be updated based on the selected negative samples. This paper proposes a pattern mining based approach to select some offenders from the negative documents, where an offender can be used to reduce the side effects of noisy features. It also classifies extracted features (i.e., terms) into three categories: positive specific terms, general terms, and negative specific terms. In this way, multiple revising strategies can be used to update extracted features. An iterative learning algorithm is also proposed to implement this approach on RCV1, and substantial experiments show that the proposed approach achieves encouraging performance.

Development of a data mining-based analysis framework for multi-attribute construction project information

Data mining techniques extract repeated and useful patterns from a large data set that in turn are utilized to predict the outcome of future events. The main purpose of the research presented in this paper is to investigate data mining strategies and develop an efficient framework for multi-attribute project information analysis to predict the performance of construction projects. The research team first reviewed existing data mining algorithms, applied them to systematically analyze a large project data set collected by the survey, and finally proposed a data-mining-based decision support framework for project performance prediction. To evaluate the potential of the framework, a case study was conducted using data collected from 139 capital projects and analyzed the relationship between use of information technology and project cost performance. The study results showed that the proposed framework has potential to promote fast, easy to use, interpretable, and accurate project data analysis.

Granule mining and its application for network traffic characterization

Decision table and decision rules play an important role in rough set based data analysis, which compress databases into granules and describe the associations between granules. Granule mining was also proposed to interpret decision rules in terms of association rules and multi-tier structure. In this paper, we further extend granule mining to describe the relationships between granules not only by traditional support and confidence, but by diversity and condition diversity as well. Diversity measures how diverse of a granule associated with the other ganules, it provides a kind of novel knowledge in databases. Some experiments are conducted to test the proposed new concepts for describing the characteristics of a real network traffic data collection. The results show that the proposed concepts are promising.

Sustainable Road Management in Texas : network-level flexible pavement structural condition analysis using data mining techniques

The research team recognized the value of network-level Falling Weight Deflectometer (FWD) testing to evaluate the structural condition trends of flexible pavements. However, practical limitations due to the cost of testing, traffic control and safety concerns and the ability to test a large network may discourage some agencies from conducting the network-level FWD testing. For this reason, the surrogate measure of the Structural Condition Index (SCI) is suggested for use. The main purpose of the research presented in this paper is to investigate data mining strategies and to develop a prediction method of the structural condition trends for network-level applications which does not require FWD testing. The research team first evaluated the existing and historical pavement condition, distress, ride, traffic and other data attributes in the Texas Department of Transportation (TxDOT) Pavement Maintenance Information System (PMIS), applied data mining strategies to the data, discovered useful patterns and knowledge for SCI value prediction, and finally provided a reasonable measure of pavement structural condition which is correlated to the SCI. To evaluate the performance of the developed prediction approach, a case study was conducted using the SCI data calculated from the FWD data collected on flexible pavements over a 5-year period (2005 – 09) from 354 PMIS sections representing 37 pavement sections on the Texas highway system. The preliminary study results showed that the proposed approach can be used as a supportive pavement structural index in the event when FWD deflection data is not available and help pavement managers identify the timing and appropriate treatment level of preventive maintenance activities.