Representing the Twittersphere: Archiving a representative sample of Twitter data under resource constraints

The rising popularity of social media posts, most notably Twitter posts, as a data source for social science research poses significant problems with regard to access to representative, high-quality data for analysis. Cheap, publicly available data such as that obtained from Twitter's public application programming interfaces is often of low quality, while high-quality data is expensive both financially and computationally. Moreover, data is often available only in real-time, making post-hoc analysis difficult or impossible. We propose and test a methodology for inexpensively creating an archive of Twitter data through population sampling, yielding a database that is highly representative of the targeted user population (in this test case, the entire population of Japanese-language Twitter users). Comparing the tweet volume, keywords, and topics found in our sample data set with the ground truth of Twitter's full data feed confirmed a very high degree of representativeness in the sample. We conclude that this approach yields a data set that is suitable for a wide range of post-hoc analyses, while remaining cost effective and accessible to a wide range of researchers.     

Intention to disclose personal information via mobile applications: A privacy calculus perspective

This study aimed to investigate the issue of consumer intention to disclose personal information via mobile applications (apps). Drawing on the literature of privacy calculus theory, this research examined the factors that influence the trade-off decision of receiving perceived benefits and being penalized with perceived risks through the calculus lens. In particular, two paths of the direct effects on perceived benefits and risks that induce the ultimate intention to disclose personal information via mobile apps were proposed and empirically tested. The analysis showed that self-presentation and personalized services positively influence consumers’ perceived benefits, which in turn positively affects the intention to disclose personal information. Perceived severity and perceived control serve as the direct antecedents of perceived risks that negatively affect the intention of consumers to disclose personal information. Compared with the perceived risks, the perceived benefits more strongly influence the intention to disclose personal information. This study extends the literature on privacy concerns to consumer intention to disclose personal information by theoretically developing and empirically testing four hypotheses in a research model. Results were validated in the mobile context, and implications and discussions were presented.     

Adapting the Knuth–Morris–Pratt algorithm for pattern matching in Huffman encoded texts

In the present work we perform compressed pattern matching in binary Huffman encoded texts [Huffman, D. (1952). A method for the construction of minimum redundancy codes, Proc. of the IRE, 40, 1098–1101]. A modified Knuth–Morris–Pratt algorithm is used in order to overcome the problem of false matches, i.e., an occurrence of the encoded pattern in the encoded text that does not correspond to an occurrence of the pattern itself in the original text. We propose a bitwise KMP algorithm that can move one extra bit in the case of a mismatch since the alphabet is binary. To avoid processing any bit of the encoded text more than once, a preprocessed table is used to determine how far to back up when a mismatch is detected, and is defined so that we are always able to align the start of the encoded pattern with the start of a codeword in the encoded text. We combine our KMP algorithm with two practical Huffman decoding schemes which handle more than a single bit per machine operation; skeleton trees defined by Klein [Klein, S. T. (2000). Skeleton trees for efficient decoding of huffman encoded texts. Information Retrieval, 3, 7–23], and numerical comparisons between special canonical values and portions of a sliding window presented in Moffat and Turpin [Moffat, A., & Turpin, A. (1997). On the implementation of minimum redundancy prefix codes. IEEE Transactions on Communications, 45, 1200–1207]. Experiments show rapid search times of our algorithms compared to the “decompress then search” method, therefore, files can be kept in their compressed form, saving memory space. When compression gain is important, these algorithms are better than cgrep [Ferragina, P., Tommasi, A., & Manzini, G. (2004). C Library to search over compressed texts, http://roquefort.di.unipi.it/~ferrax/CompressedSearch], which is only slightly faster than ours.     

基于数据仓库的咨询管理模式研究

本文在分析我国咨询服务业目前发展状况的基础上 ,设计了基于数据仓库的咨询管理模式 ,描述了其结构和功能     

Ethical issues in web data mining

Web mining refers to the whole of data miningand related techniques that are used toautomatically discover and extract informationfrom web documents and services. When used in abusiness context and applied to some type ofpersonal data, it helps companies to builddetailed customer profiles, and gain marketingintelligence. Web mining does, however, pose athreat to some important ethical values likeprivacy and individuality. Web mining makes itdifficult for an individual to autonomouslycontrol the unveiling and dissemination of dataabout his/her private life. To study thesethreats, we distinguish between `content andstructure mining' and `usage mining.' Webcontent and structure mining is a cause forconcern when data published on the web in acertain context is mined and combined withother data for use in a totally differentcontext. Web usage mining raises privacyconcerns when web users are traced, and theiractions are analysed without their knowledge.Furthermore, both types of web mining are oftenused to create customer files with a strongtendency of judging and treating people on thebasis of group characteristics instead of ontheir own individual characteristics and merits(referred to as de-individualisation). Althoughthere are a variety of solutions toprivacy-problems, none of these solutionsoffers sufficient protection. Only a combinedsolution package consisting of solutions at anindividual as well as a collective level cancontribute to release some of the tensionbetween the advantages and the disadvantages ofweb mining. The values of privacy andindividuality should be respected and protectedto make sure that people are judged and treatedfairly. People should be aware of theseriousness of the dangers and continuouslydiscuss these ethical issues. This should be ajoint responsibility shared by web miners (bothadopters and developers), web users, andgovernments.     

网络入侵检测中的数据挖掘技术探讨

针对计算机网络的入侵越来越严重，本文论述了数据挖掘技术在网络入侵检测中的应用，指出了审计数据的挖掘方法及挖掘模式的使用。     

Cyberstalking, personal privacy, and moral responsibility

This essay examines some ethical aspects of stalkingincidents in cyberspace. Particular attention is focused on the Amy Boyer/Liam Youens case of cyberstalking, which has raised a number of controversial ethical questions. We limit our analysis to three issues involving this particular case. First, we suggest that the privacy of stalking victims is threatened because of the unrestricted access to on-linepersonal information, including on-line public records, currently available to stalkers. Second, we consider issues involving moral responsibility and legal liability for Internet service providers (ISPs) when stalking crimesoccur in their `space' on the Internet. Finally, we examine issues of moral responsibility for ordinary Internet users to determine whether they are obligated to inform persons whom they discover to be the targets of cyberstalkers.     

Informational privacy and moral values

A case from 1996 in Oregon in which citizens' legally publicmotor vehicle information was disseminated on a World Wide Website is considered. The case evoked widespread moral outrageamong Oregonians and led to changes in the Oregon records laws.The application of either consequentialist ornon-consequentialist moral theories to this and otherinformational privacy cases is found to be inadequate.Adjudication of conflicting desires is offered as the appropriateanalytical model for moral disputes. The notion of adjudicationoffered here diverges from traditional moral theories in itsindeterminate nature.     

Misconceptions about data-based decision making in education: An exploration of the literature

Research on data-based decision making has proliferated around the world, fueled by policy recommendations and the diverse data that are now available to educators to inform their practice. Yet, many misconceptions and concerns have been raised by researchers and practitioners. To better understand the issues, a session was convened at AERA’s annual convention in 2018, followed by an analysis of the literature based on misconceptions that emerged. This commentary is an outgrowth of that exploration by providing research, theoretical, and practical evidence to dispel some of the misconceptions. Our objective is to survey and synthesize the landscape of the data-based decision making literature to address the identified misconceptions and then to serve as a stimulus to changes in policy and practice as well as a roadmap for a research agenda.     

Sorting pupils into their next educational track: How strongly do teachers rely on data-based or intuitive processes when they make the transition decision?

For many years, teachers’ intuitive evaluations of pupils’ competences was considered to be a solid base for decisions; it is only recently that teachers have been expected more and more to use data. We state that insights on intuitive and data-driven approaches need to be integrated to understand and support informed, professional decisions in education. Starting from an integrated framework we studied teachers’ decision process regarding the transition of 30 pupils during their last year of primary education within a case study design. Results describe different approaches to decision-making. Some teachers greatly rely on intuitive processes when they ultimately make the decision, even if data was collected. Other teachers combine and weigh information deriving from deliberate processes of data use and from intuitive recognition before they decide. Implications for theory and practice are explained.