Search (159 results, page 2 of 8)

0.0029000505 = product of:
  0.005800101 = sum of:
    0.005800101 = product of:
      0.011600202 = sum of:
        0.011600202 = weight(_text_:a in 2338) [ClassicSimilarity], result of:
          0.011600202 = score(doc=2338,freq=12.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.21843673 = fieldWeight in 2338, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2338)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Hundreds of thousands of hashtags are generated every day on Twitter. Only a few will burst and become trending topics. In this article, we provide the definition of a bursting hashtag and conduct a systematic study of a series of challenging prediction problems that span the entire life cycles of bursting hashtags. Around the problem of "how to build a system to predict bursting hashtags," we explore different types of features and present machine learning solutions. On real data sets from Twitter, experiments are conducted to evaluate the effectiveness of the proposed solutions and the contributions of features.

Type

a

0.0028703054 = product of:
  0.005740611 = sum of:
    0.005740611 = product of:
      0.011481222 = sum of:
        0.011481222 = weight(_text_:a in 517) [ClassicSimilarity], result of:
          0.011481222 = score(doc=517,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.2161963 = fieldWeight in 517, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=517)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This study investigates the argument patterns in Yahoo! Answers, a major question and answer (Q&A) site. Mainly drawing on the ideas of Toulmin (), argument pattern is conceptualized as a set of 5 major elements: claim, counterclaim, rebuttal, support, and grounds. The combinations of these elements result in diverse argument patterns. Failed opening consists of an initial claim only, whereas nonoppositional argument pattern also includes indications of support. Oppositional argument pattern contains the elements of counterclaim and rebuttal. Mixed argument pattern entails all 5 elements. The empirical data were gathered by downloading from Yahoo! Answers 100 discussion threads discussing global warming-a controversial topic providing a fertile ground for arguments for and against. Of the argument patterns, failed openings were most frequent, followed by oppositional, nonoppositional, and mixed patterns. In most cases, the participants grounded their arguments by drawing on personal beliefs and facts. The findings suggest that oppositional and mixed argument patterns provide more opportunities for the assessment of the quality and credibility of answers, as compared to failed openings and nonoppositional argument patterns.

Type

a

0.0028047764 = product of:
  0.005609553 = sum of:
    0.005609553 = product of:
      0.011219106 = sum of:
        0.011219106 = weight(_text_:a in 3702) [ClassicSimilarity], result of:
          0.011219106 = score(doc=3702,freq=22.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.21126054 = fieldWeight in 3702, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3702)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Politicians' Web sites have been considered a medium for organizing, mobilizing, and agenda-setting, but extant literature lacks a systematic approach to interpret the Web sites of senators - a new medium for political communication. This study classifies the role of political Web sites into relational (hyperlinking) and topical (shared-issues) aspects. The two aspects may be viewed from a social embeddedness perspective and three facets, as K. Foot and S. Schneider ([2002]) suggested. This study employed network analysis, a set of research procedures for identifying structures in social systems, as the basis of the relations among the system's components rather than the attributes of individuals. Hyperlink and issue data were gathered from the United States Senate Web site and Yahoo. Major findings include: (a) The hyperlinks are more targeted at Democratic senators than at Republicans and are a means of communication for senators and users; (b) the issue network found from the Web is used for discussing public agendas and is more highly utilized by Republican senators; (c) the hyperlink and issue networks are correlated; and (d) social relationships and issue ecologies can be effectively detected by these two networks. The need for further research is addressed.

Type

a

0.0028047764 = product of:
  0.005609553 = sum of:
    0.005609553 = product of:
      0.011219106 = sum of:
        0.011219106 = weight(_text_:a in 4976) [ClassicSimilarity], result of:
          0.011219106 = score(doc=4976,freq=22.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.21126054 = fieldWeight in 4976, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4976)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

As online communities grow and the volume of user-generated content increases, the need for community management also rises. Community management has three main purposes: to create a positive experience for existing participants, to promote appropriate, socionormative behaviors, and to encourage potential participants to make contributions. Research indicates that the quality of content a potential participant sees on a site is highly influential; off-topic, negative comments with malicious intent are a particularly strong boundary to participation or set the tone for encouraging similar contributions. A problem for community managers, therefore, is the detection and elimination of such undesirable content. As a community grows, this undertaking becomes more daunting. Can an automated system aid community managers in this task? In this paper, we address this question through a machine learning approach to automatic detection of inappropriate negative user contributions. Our training corpus is a set of comments from a news commenting site that we tasked Amazon Mechanical Turk workers with labeling. Each comment is labeled for the presence of profanity, insults, and the object of the insults. Support vector machines trained on these data are combined with relevance and valence analysis systems in a multistep approach to the detection of inappropriate negative user contributions. The system shows great potential for semiautomated community management.

Type

a

0.0028047764 = product of:
  0.005609553 = sum of:
    0.005609553 = product of:
      0.011219106 = sum of:
        0.011219106 = weight(_text_:a in 51) [ClassicSimilarity], result of:
          0.011219106 = score(doc=51,freq=22.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.21126054 = fieldWeight in 51, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=51)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Multisource web news portals provide various advantages such as richness in news content and an opportunity to follow developments from different perspectives. However, in such environments, news variety and quantity can have an overwhelming effect. New-event detection and topic-tracking studies address this problem. They examine news streams and organize stories according to their events; however, several tracking stories of an event/topic may contain no new information (i.e., no novelty). We study the novelty detection (ND) problem on the tracking news of a particular topic. For this purpose, we build a Turkish ND test collection called BilNov-2005 and propose the usage of three ND methods: a cosine-similarity (CS)-based method, a language-model (LM)-based method, and a cover-coefficient (CC)-based method. For the LM-based ND method, we show that a simpler smoothing approach, Dirichlet smoothing, can have similar performance to a more complex smoothing approach, Shrinkage smoothing. We introduce a baseline that shows the performance of a system with random novelty decisions. In addition, a category-based threshold learning method is used for the first time in ND literature. The experimental results show that the LM-based ND method significantly outperforms the CS- and CC-based methods, and category-based threshold learning achieves promising results when compared to general threshold learning.

Type

a

0.0028047764 = product of:
  0.005609553 = sum of:
    0.005609553 = product of:
      0.011219106 = sum of:
        0.011219106 = weight(_text_:a in 3215) [ClassicSimilarity], result of:
          0.011219106 = score(doc=3215,freq=22.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.21126054 = fieldWeight in 3215, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3215)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Twitter is used by a substantial minority of the populations of many countries to share short messages, sometimes including images. Nevertheless, despite some research into specific images, such as selfies, and a few news stories about specific tweeted photographs, little is known about the types of images that are routinely shared. In response, this article reports a content analysis of random samples of 800 images tweeted from the UK or USA during a week at the end of 2014. Although most images were photographs, a substantial minority were hybrid or layered image forms: phone screenshots, collages, captioned pictures, and pictures of text messages. About half were primarily of one or more people, including 10% that were selfies, but a wide variety of other things were also pictured. Some of the images were for advertising or to share a joke but in most cases the purpose of the tweet seemed to be to share the minutiae of daily lives, performing the function of chat or gossip, sometimes in innovative ways.

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 505) [ClassicSimilarity], result of:
          0.0108246 = score(doc=505,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 505, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0625 = fieldNorm(doc=505)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The behavior of modern web robots varies widely when they crawl for different purposes. In this article, we present a framework to classify these web robots from two orthogonal perspectives, namely, their functionality and the types of resources they consume. Applying the classification framework to a year-long access log from the UConn SoE web server, we present trends that point to significant differences in their crawling behavior.

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 3433) [ClassicSimilarity], result of:
          0.010739701 = score(doc=3433,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 3433, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=3433)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Despite the development of huge healthcare Web sites and powerful search engines, many searchers end their searches prematurely with incomplete information. Recent studies suggest that users often retrieve incomplete information because of the complex scatter of relevant facts about a topic across Web pages. However, little is understood about regularities underlying such information scatter. To probe regularities within the scatter of facts across Web pages, this article presents the results of two analyses: (a) a cluster analysis of Web pages that reveals the existence of three page clusters that vary in information density and (b) a content analysis that suggests the role each of the above-mentioned page clusters play in providing comprehensive information. These results provide implications for the design of Web sites, search tools, and training to help users find comprehensive information about a topic and for a hypothesis describing the underlying mechanisms causing the scatter. We conclude by briefly discussing how the analysis of information scatter, at the granularity of facts, complements existing theories of information-seeking behavior.

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 4230) [ClassicSimilarity], result of:
          0.010739701 = score(doc=4230,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 4230, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=4230)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article presents conceptual navigation and NavCon, an architecture that implements this navigation in World Wide Web pages. NavCon architecture makes use of ontology as metadata to contextualize user search for information. Based on ontologies, NavCon automatically inserts conceptual links in Web pages. By using these links, the user may navigate in a graph representing ontology concepts and their relationships. By browsing this graph, it is possible to reach documents associated with the user desired ontology concept. This Web navigation supported by ontology concepts we call conceptual navigation. Conceptual navigation is a technique to browse Web sites within a context. The context filters relevant retrieved information. The context also drives user navigation through paths that meet his needs. A company may implement conceptual navigation to improve user search for information in a knowledge management environment. We suggest that the use of an ontology to conduct navigation in an Intranet may help the user to have a better understanding about the knowledge structure of the company.

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 4772) [ClassicSimilarity], result of:
          0.010739701 = score(doc=4772,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 4772, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=4772)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article describes the outcomes of research that examined the practice of web information architecture (IA) in large organizations. Using a grounded theory approach, seven large organizations were investigated and the data were analyzed for emerging themes and concepts. The research finds that the practice of web IA is characterized by unpredictability, multiple perspectives, and a need for responsiveness, agility, and negotiation. This article claims that web IA occurs in a complex environment and has emergent, self-organizing properties. There is value in examining the practice as a complex adaptive system. Using this metaphor, a pre-determined, structured methodology that delivers a documented, enduring, information design for the web is found inadequate - dominant and traditional thinking and practice in the organization of information are challenged.

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 254) [ClassicSimilarity], result of:
          0.010739701 = score(doc=254,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 254, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=254)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article discusses people's understanding of reality by representations from the Internet. The Hegelian inquiry system is used here to explain the nature of informing on the Internet as activities of information masters to influence information slaves' opinions and as activities of information slaves to become well informed. The key assumption of Hegelianism regarding information is that information has no value independent from the interests and worldviews (theses) it supports. As part of the dialectic process of generating syntheses, we propose a role for information science of offering methods to critically evaluate the master's information, and by this we develop an opinion (thesis) independent from the master's power. For this we offer multiple methods for information criticism, named triangulation, which may help users to evaluate a master's evidence. This article presents also a prototype of a Hegelian information triangulator tool for information slaves (i.e., nonexperts). The article concludes with suggestions for further research on informative triangulation.

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 1661) [ClassicSimilarity], result of:
          0.010739701 = score(doc=1661,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 1661, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=1661)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

In this work, we explore the types of triggers that spark trends on Twitter, introducing a typology with the following 4 types: news, ongoing events, memes, and commemoratives. While previous research has analyzed trending topics over the long term, we look at the earliest tweets that produce a trend, with the aim of categorizing trends early on. This allows us to provide a filtered subset of trends to end users. We experiment with a set of straightforward language-independent features based on the social spread of trends and categorize them using the typology. Our method provides an efficient way to accurately categorize trending topics without need of external data, enabling news organizations to discover breaking news in real-time, or to quickly identify viral memes that might inform marketing decisions, among others. The analysis of social features also reveals patterns associated with each type of trend, such as tweets about ongoing events being shorter as many were likely sent from mobile devices, or memes having more retweets originating from a few trend-setters.

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 4683) [ClassicSimilarity], result of:
          0.010739701 = score(doc=4683,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 4683, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=4683)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Basic human values represent what we think are important to our lives that include security, independence, success, kindness, and pleasure. Each of us holds different values with different degrees of importance. Existing studies show that values of a person can be identified from their social network usage. However, the value priority of a person may change over time due to different factors such as time, event, influence, social structure, and technology. In this research, we are the first to investigate whether the change of value priorities can be identified from social network usage. We propose a weighted hybrid time-series-based model to capture the change of values of a social network user. We conducted an experimental study with 726 Facebook users and showed that our model accurately captures the value priority changes from the social network usage and achieves significantly higher accuracy than our baseline hidden Markov model-based technique. We also validated the change of a user's value priorities in real life using a questionnaire-based technique.

Type

a

0.0026742492 = product of:
  0.0053484985 = sum of:
    0.0053484985 = product of:
      0.010696997 = sum of:
        0.010696997 = weight(_text_:a in 2335) [ClassicSimilarity], result of:
          0.010696997 = score(doc=2335,freq=20.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20142901 = fieldWeight in 2335, product of:
              4.472136 = tf(freq=20.0), with freq of:
                20.0 = termFreq=20.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2335)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Spam and wildly varying documents make searching in Twitter challenging. Most Twitter search systems generally treat a Tweet as a plain text when modeling relevance. However, a series of conventions allows users to Tweet in structural ways using a combination of different blocks of texts. These blocks include plain texts, hashtags, links, mentions, etc. Each block encodes a variety of communicative intent and the sequence of these blocks captures changing discourse. Previous work shows that exploiting the structural information can improve the structured documents (e.g., web pages) retrieval. In this study we utilize the structure of Tweets, induced by these blocks, for Twitter retrieval and Twitter opinion retrieval. For Twitter retrieval, a set of features, derived from the blocks of text and their combinations, is used into a learning-to-rank scenario. We show that structuring Tweets can achieve state-of-the-art performance. Our approach does not rely on social media features, but when we do add this additional information, performance improves significantly. For Twitter opinion retrieval, we explore the question of whether structural information derived from the body of Tweets and opinionatedness ratings of Tweets can improve performance. Experimental results show that retrieval using a novel unsupervised opinionatedness feature based on structuring Tweets achieves comparable performance with a supervised method using manually tagged Tweets. Topic-related specific structured Tweet sets are shown to help with query-dependent opinion retrieval.

Type

a

0.0026742492 = product of:
  0.0053484985 = sum of:
    0.0053484985 = product of:
      0.010696997 = sum of:
        0.010696997 = weight(_text_:a in 5292) [ClassicSimilarity], result of:
          0.010696997 = score(doc=5292,freq=20.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20142901 = fieldWeight in 5292, product of:
              4.472136 = tf(freq=20.0), with freq of:
                20.0 = termFreq=20.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5292)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The Internet has become the first source of consumer health information. Most theoretical and empirical studies are centered on information needs and seeking, rather than on information outcomes. This review's purpose is to explore and explain health outcomes of Online Consumer Health Information (OCHI) in primary care. A participatory systematic mixed studies review with a framework synthesis was undertaken. Starting from an initial conceptual framework, our specific objectives were to (a) identify types of OCHI outcomes in primary care, (b) identify factors associated with these outcomes, and (c) integrate these factors and outcomes into a comprehensive revised framework combining an information theory and a psychosocial theory of behavior. The results of 65 included studies were synthesized using a qualitative thematic data analysis. The themes derived from the literature underwent a harmonization process that produced a comprehensive typology of OCHI outcomes. The revised conceptual framework specifies four individual and one organizational level of OCHI outcomes, while including factors such as consumers' information needs and four interdependent contextual factors. It contributes to theoretical knowledge about OCHI health outcomes, and informs future research, information assessment methods, and tools to help consumers find and use health information.

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 1248) [ClassicSimilarity], result of:
          0.010589487 = score(doc=1248,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 1248, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1248)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article estimates the first constant quality price index for Internet domain names. The suggested index provides a benchmark for domain name traders and investors looking for information on price trends, historical returns, and the fundamental risk of Internet domain names. The index increases transparency in the market for this newly emerged asset class. A cointegration analysis shows that domain registrations and resale prices form a long-run equilibrium and indicates supply constraints in domain space. This study explores a large data set of domain sales spanning the years 2006 to 2013. Differences in the quality of individual domain names are controlled for in hedonic repeat sales regressions.

Type

a

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 4450) [ClassicSimilarity], result of:
          0.010148063 = score(doc=4450,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 4450, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4450)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Web data repositories usually contain references to thousands of real-world entities from multiple sources. It is not uncommon that multiple entities share the same label (polysemes) and that distinct label variations are associated with the same entity (synonyms), which frequently leads to ambiguous interpretations. Further, spelling variants, acronyms, abbreviated forms, and misspellings compound to worsen the problem. Solving this problem requires identifying which labels correspond to the same real-world entity, a process known as entity resolution. One approach to solve the entity resolution problem is to associate an authority identifier and a list of variant forms with each entity-a data structure known as an authority file. In this work, we propose a generic framework for implementing a method for generating authority files. Our method uses information from the Web to improve the quality of the authority file and, because of that, is referred to as WER-Web-based Entity Resolution. Our contribution here is threefold: (a) we discuss how to implement the WER framework, which is flexible and easy to adapt to new domains; (b) we run extended experimentation with our WER framework to show that it outperforms selected baselines; and (c) we compare the results of a specialized solution for author name resolution with those produced by the generic WER framework, and show that the WER results remain competitive.

Type

a

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 4988) [ClassicSimilarity], result of:
          0.010148063 = score(doc=4988,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 4988, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4988)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article presents a search-intent-based method to generate pornographic blacklists for collaborative cyberporn filtering. A novel porn-detection framework that can find newly appearing pornographic web pages by mining search query logs is proposed. First, suspected queries are identified along with their clicked URLs by an automatically constructed lexicon. Then, a candidate URL is determined if the number of clicks satisfies majority voting rules. Finally, a candidate whose URL contains at least one categorical keyword will be included in a blacklist. Several experiments are conducted on an MSN search porn dataset to demonstrate the effectiveness of our method. The resulting blacklist generated by our search-intent-based method achieves high precision (0.701) while maintaining a favorably low false-positive rate (0.086). The experiments of a real-life filtering simulation reveal that our proposed method with its accumulative update strategy can achieve 44.15% of a macro-averaging blocking rate, when the update frequency is set to 1 day. In addition, the overblocking rates are less than 9% with time change due to the strong advantages of our search-intent-based method. This user-behavior-oriented method can be easily applied to search engines for incorporating only implicit collective intelligence from query logs without other efforts. In practice, it is complementary to intelligent content analysis for keeping up with the changing trails of objectionable websites from users' perspectives.

Type

a

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 3009) [ClassicSimilarity], result of:
          0.010148063 = score(doc=3009,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 3009, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3009)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Although the Internet has become a major source for accessing news, there is little research regarding users' experience with news sites. We conducted an experiment to test a comprehensive model of user experience with news sites that was developed previously by means of an online survey. Level of adoption (novel or adopted site) was controlled with a between-subjects manipulation. We collected participants' answers to psychometric scales at 2 times: after presentation of 5 screenshots of a news site and directly after 10 minutes of hands-on experience with the site. The model was extended with the prediction of users' satisfaction with news sites as a high-level design goal. A psychometric measure of trust in news providers was developed and added to the model to better predict people's intention to use particular news sites. The model presented in this article represents a theoretically founded, empirically tested basis for evaluating news websites, and it holds theoretical relevance to user-experience research in general. Finally, the findings and the model are applied to provide practical guidance in design prioritization.

Type

a

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 5301) [ClassicSimilarity], result of:
          0.010148063 = score(doc=5301,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 5301, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5301)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Given the task of finding influencers (opinion makers) for a given domain in a social network, we investigate (a) what is the relative importance of domain and authority signals, (b) what is the most effective way of combining signals (voting, classification, learning to rank, etc.) and how best to model the vocabulary signal, and (c) how large is the gap between supervised and unsupervised methods and what are the practical consequences. Our best results on the RepLab dataset (which improves the state of the art) uses language models to learn the domain-specific vocabulary used by influencers and combines domain and authority models using a Learning to Rank algorithm. Our experiments show that (a) both authority and domain evidence can be trained from the vocabulary of influencers; (b) once the language of influencers is modeled as a likelihood signal, further supervised learning and additional network-based signals only provide marginal improvements; and (c) the availability of training data sets is crucial to obtain competitive results in the task. Our most remarkable finding is that influencers do use a distinctive vocabulary, which is a more reliable signal than nontextual network indicators such as the number of followers, retweets, and so on.

Type

a