Search (138 results, page 7 of 7)

0.004709213 = product of:
  0.011773032 = sum of:
    0.008615503 = weight(_text_:a in 5701) [ClassicSimilarity], result of:
      0.008615503 = score(doc=5701,freq=20.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.16114321 = fieldWeight in 5701, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.03125 = fieldNorm(doc=5701)
    0.003157529 = product of:
      0.006315058 = sum of:
        0.006315058 = weight(_text_:information in 5701) [ClassicSimilarity], result of:
          0.006315058 = score(doc=5701,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.0775819 = fieldWeight in 5701, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.03125 = fieldNorm(doc=5701)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

A user-centered investigation of interactive query expansion within the context of a relevance feedback system is presented in this article. Data were collected from 25 searches using the INSPEC database. The data collection mechanisms included questionnaires, transaction logs, and relevance evaluations. The results discuss issues that relate to query expansion, retrieval effectiveness, the correspondence of the on-line-to-off-line relevance judgments, and the selection of terms for query expansion by users (interactive query expansion). The main conclusions drawn from the results of the study are that: (1) one-third of the terms presented to users in a list of candidate terms for query expansion was identified by the users as potentially useful for query expansion. (2) These terms were mainly judged as either variant expressions (synonyms) or alternative (related) terms to the initial query terms. However, a substantial portion of the selected terms were identified as representing new ideas. (3) The relationships identified between the five best terms selected by the users for query expansion and the initial query terms were that: (a) 34% of the query expansion terms have no relationship or other type of correspondence with a query term; (b) 66% of the remaining query expansion terms have a relationship to the query terms. These relationships were: narrower term (46%), broader term (3%), related term (17%). (4) The results provide evidence for the effectiveness of interactive query expansion. The initial search produced on average three highly relevant documents; the query expansion search produced on average nine further highly relevant documents. The conclusions highlight the need for more research on: interactive query expansion, the comparative evaluation of automatic vs. interactive query expansion, the study of weighted Webbased or Web-accessible retrieval systems in operational environments, and for user studies in searching ranked retrieval systems in general

Source

Journal of the American Society for Information Science. 51(2000) no.11, S.989-1003

Type

a

0.004624805 = product of:
  0.011562012 = sum of:
    0.0076151006 = weight(_text_:a in 819) [ClassicSimilarity], result of:
      0.0076151006 = score(doc=819,freq=10.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.14243183 = fieldWeight in 819, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=819)
    0.003946911 = product of:
      0.007893822 = sum of:
        0.007893822 = weight(_text_:information in 819) [ClassicSimilarity], result of:
          0.007893822 = score(doc=819,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.09697737 = fieldWeight in 819, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0390625 = fieldNorm(doc=819)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

Purpose - An issue that tends to be ignored in information retrieval is the issue of updating inverted files. This is largely because inverted files were devised to provide fast query service, and much work has been done with the emphasis strongly on queries. This paper aims to study the effect of using parallel methods for the update of inverted files in order to reduce costs, by looking at two types of partitioning for inverted files: document identifier and term identifier. Design/methodology/approach - Raw update service and update with query service are studied with these partitioning schemes using an incremental update strategy. The paper uses standard measures used in parallel computing such as speedup to examine the computing results and also the costs of reorganising indexes while servicing transactions. Findings - Empirical results show that for both transaction processing and index reorganisation the document identifier method is superior. However, there is evidence that the term identifier partitioning method could be useful in a concurrent transaction processing context. Practical implications - There is an increasing need to service updates, which is now becoming a requirement of inverted files (for dynamic collections such as the web), demonstrating that a shift in requirements of inverted file maintenance is needed from the past. Originality/value - The paper is of value to database administrators who manage large-scale and dynamic text collections, and who need to use parallel computing to implement their text retrieval services.

Type

a

0.004624805 = product of:
  0.011562012 = sum of:
    0.0076151006 = weight(_text_:a in 4296) [ClassicSimilarity], result of:
      0.0076151006 = score(doc=4296,freq=10.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.14243183 = fieldWeight in 4296, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4296)
    0.003946911 = product of:
      0.007893822 = sum of:
        0.007893822 = weight(_text_:information in 4296) [ClassicSimilarity], result of:
          0.007893822 = score(doc=4296,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.09697737 = fieldWeight in 4296, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4296)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

Daffodil is a front-end to federated, heterogeneous digital libraries targeting at strategic support of users during the information seeking process. This is done by offering a variety of functions for searching, exploring and managing digital library objects. However, the distributed search increases response time and the conceptual model of the underlying search processes is inherently weaker. This makes query formulation harder and the resulting waiting times can be frustrating. In this paper, we investigate the concept of proactive support during the user's query formulation. For improving user efficiency and satisfaction, we implemented annotations, proactive support and error markers on the query form itself. These functions decrease the probability for syntactical or semantical errors in queries. Furthermore, the user is able to make better tactical decisions and feels more confident that the system handles the query properly. Evaluations with 30 subjects showed that user satisfaction is improved, whereas no conclusive results were received for efficiency.

Type

a

0.0044313995 = product of:
  0.011078498 = sum of:
    0.002724461 = weight(_text_:a in 7) [ClassicSimilarity], result of:
      0.002724461 = score(doc=7,freq=2.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.050957955 = fieldWeight in 7, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.03125 = fieldNorm(doc=7)
    0.008354037 = product of:
      0.016708074 = sum of:
        0.016708074 = weight(_text_:information in 7) [ClassicSimilarity], result of:
          0.016708074 = score(doc=7,freq=14.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.20526241 = fieldWeight in 7, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.03125 = fieldNorm(doc=7)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

The second edition of Understanding Search Engines: Mathematical Modeling and Text Retrieval follows the basic premise of the first edition by discussing many of the key design issues for building search engines and emphasizing the important role that applied mathematics can play in improving information retrieval. The authors discuss important data structures, algorithms, and software as well as user-centered issues such as interfaces, manual indexing, and document preparation. Significant changes bring the text up to date on current information retrieval methods: for example the addition of a new chapter on link-structure algorithms used in search engines such as Google. The chapter on user interface has been rewritten to specifically focus on search engine usability. In addition the authors have added new recommendations for further reading and expanded the bibliography, and have updated and streamlined the index to make it more reader friendly.

Content

Inhalt: Introduction Document File Preparation - Manual Indexing - Information Extraction - Vector Space Modeling - Matrix Decompositions - Query Representations - Ranking and Relevance Feedback - Searching by Link Structure - User Interface - Book Format Document File Preparation Document Purification and Analysis - Text Formatting - Validation - Manual Indexing - Automatic Indexing - Item Normalization - Inverted File Structures - Document File - Dictionary List - Inversion List - Other File Structures Vector Space Models Construction - Term-by-Document Matrices - Simple Query Matching - Design Issues - Term Weighting - Sparse Matrix Storage - Low-Rank Approximations Matrix Decompositions QR Factorization - Singular Value Decomposition - Low-Rank Approximations - Query Matching - Software - Semidiscrete Decomposition - Updating Techniques Query Management Query Binding - Types of Queries - Boolean Queries - Natural Language Queries - Thesaurus Queries - Fuzzy Queries - Term Searches - Probabilistic Queries Ranking and Relevance Feedback Performance Evaluation - Precision - Recall - Average Precision - Genetic Algorithms - Relevance Feedback Searching by Link Structure HITS Method - HITS Implementation - HITS Summary - PageRank Method - PageRank Adjustments - PageRank Implementation - PageRank Summary User Interface Considerations General Guidelines - Search Engine Interfaces - Form Fill-in - Display Considerations - Progress Indication - No Penalties for Error - Results - Test and Retest - Final Considerations Further Reading

RSWK

Suchmaschine / Information Retrieval
Suchmaschine / Information Retrieval / Mathematisches Modell (HEBIS)

Subject

Suchmaschine / Information Retrieval
Suchmaschine / Information Retrieval / Mathematisches Modell (HEBIS)

0.004313929 = product of:
  0.0107848225 = sum of:
    0.004086692 = weight(_text_:a in 193) [ClassicSimilarity], result of:
      0.004086692 = score(doc=193,freq=2.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.07643694 = fieldWeight in 193, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=193)
    0.0066981306 = product of:
      0.013396261 = sum of:
        0.013396261 = weight(_text_:information in 193) [ClassicSimilarity], result of:
          0.013396261 = score(doc=193,freq=4.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.16457605 = fieldWeight in 193, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=193)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

The view of documents and/or queries as random variables is gaining importance in the theory of information retrieval. We argue that traditional probabilistic models consider documents and queries as random variables, but that newer models such as language modeling and our unified model take this one step further. The additional step is called error in predictors. Such models consider that we don't observe the document and query random variables that are modeled to predict relevance probabilistically. Rather, there are additional random variables, which are the observed documents and queries. We discuss some important implications of this idea for parameter estimation, relevance prediction, and even test-collection construction. By clarifying the positions of various probabilistic models on this question, and presenting in one place many of its implications, this article aims to deepen our common understanding of the theories behind traditional probabilistic models, and to strengthen the theoretical basis for further development of more recent approaches such as language modeling.

Source

Journal of the American Society for Information Science and Technology. 57(2006) no.9, S.1138-1154

Type

a

0.004303226 = product of:
  0.010758064 = sum of:
    0.0068111527 = weight(_text_:a in 2756) [ClassicSimilarity], result of:
      0.0068111527 = score(doc=2756,freq=8.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.12739488 = fieldWeight in 2756, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2756)
    0.003946911 = product of:
      0.007893822 = sum of:
        0.007893822 = weight(_text_:information in 2756) [ClassicSimilarity], result of:
          0.007893822 = score(doc=2756,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.09697737 = fieldWeight in 2756, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2756)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

We evaluated the different genetic algorithms applied to relevance feedback that are to be found in the literature and which follow the vector space model (the most commonly used model in this type of application). They were compared with a traditional relevance feedback algorithm - the Ide dec-hi method - since this had given the best results in the study of Salton & Buckley (1990) an this subject. The experiment was performed an the Cranfield collection, and the different algorithms were evaluated using the residual collection method (one of the most suitable methods for evaluating relevance feedback techniques). The results varied greatly depending an the fitness function that was used, from no improvement in some of the genetic algorithms, to a more than 127% improvement with one algorithm, surpassing even the traditional Ide dec-hi method. One can therefore conclude that genetic algorithms show great promise as an aid to implementing a truly effective information retrieval system.

Type

a

0.0042062993 = product of:
  0.0105157485 = sum of:
    0.005779455 = weight(_text_:a in 4295) [ClassicSimilarity], result of:
      0.005779455 = score(doc=4295,freq=4.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.10809815 = fieldWeight in 4295, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046875 = fieldNorm(doc=4295)
    0.0047362936 = product of:
      0.009472587 = sum of:
        0.009472587 = weight(_text_:information in 4295) [ClassicSimilarity], result of:
          0.009472587 = score(doc=4295,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.116372846 = fieldWeight in 4295, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=4295)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

The issue of reducing the space overhead when indexing large text databases is becoming more and more important, as the text collection grow in size. Another subject, which is gaining importance as text databases grow and get more heterogeneous and error prone, is that of flexible string matching. One of the best tools to make the search more flexible is to allow a limited number of differences between the words found and those sought. This is called 'approximate text searching'. which is becoming more and more popular. In recent years some indexing schemes with very low space overhead have appeared, some of them dealing with approximate searching. These low overhead indices (whose most notorious exponent is Glimpse) are modified inverted files, where space is saved by making the lists of occurences point to text blocks instead of exact word positions. Despite their existence, little is known about the expected behaviour of these 'block addressing' indices, and even less is known when it comes to cope with approximate search. Our main contribution is an analytical study of the space-time trade-offs for indexed text searching

Source

Journal of the American Society for Information Science. 51(2000) no.1, S.69-82

Type

a

0.0039382176 = product of:
  0.009845544 = sum of:
    0.005898632 = weight(_text_:a in 2069) [ClassicSimilarity], result of:
      0.005898632 = score(doc=2069,freq=6.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.11032722 = fieldWeight in 2069, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2069)
    0.003946911 = product of:
      0.007893822 = sum of:
        0.007893822 = weight(_text_:information in 2069) [ClassicSimilarity], result of:
          0.007893822 = score(doc=2069,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.09697737 = fieldWeight in 2069, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2069)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

The semantic web not only contains resources but also includes the heterogeneous relationships among them, which is sharply distinguished from the current web. As the growth of the semantic web, specialized search techniques are of significance. In this paper, we present RSS-a framework for enabling ranked semantic search on the semantic web. In this framework, the heterogeneity of relationships is fully exploited to determine the global importance of resources. In addition, the search results can be greatly expanded with entities most semantically related to the query, thus able to provide users with properly ordered semantic search results by combining global ranking values and the relevance between the resources and the query. The proposed semantic search model which supports inference is very different from traditional keyword-based search methods. Moreover, RSS also distinguishes from many current methods of accessing the semantic web data in that it applies novel ranking strategies to prevent returning search results in disorder. The experimental results show that the framework is feasible and can produce better ordering of semantic search results than directly applying the standard PageRank algorithm on the semantic web.

Source

Information processing and management. 44(2008) no.2, S.893-909

Type

a

0.003752812 = product of:
  0.00938203 = sum of:
    0.004086692 = weight(_text_:a in 6) [ClassicSimilarity], result of:
      0.004086692 = score(doc=6,freq=8.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.07643694 = fieldWeight in 6, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0234375 = fieldNorm(doc=6)
    0.0052953376 = product of:
      0.010590675 = sum of:
        0.010590675 = weight(_text_:information in 6) [ClassicSimilarity], result of:
          0.010590675 = score(doc=6,freq=10.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.1301088 = fieldWeight in 6, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0234375 = fieldNorm(doc=6)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Content

Inhalt: Chapter 1. Introduction to Web Search Engines: 1.1 A Short History of Information Retrieval - 1.2 An Overview of Traditional Information Retrieval - 1.3 Web Information Retrieval Chapter 2. Crawling, Indexing, and Query Processing: 2.1 Crawling - 2.2 The Content Index - 2.3 Query Processing Chapter 3. Ranking Webpages by Popularity: 3.1 The Scene in 1998 - 3.2 Two Theses - 3.3 Query-Independence Chapter 4. The Mathematics of Google's PageRank: 4.1 The Original Summation Formula for PageRank - 4.2 Matrix Representation of the Summation Equations - 4.3 Problems with the Iterative Process - 4.4 A Little Markov Chain Theory - 4.5 Early Adjustments to the Basic Model - 4.6 Computation of the PageRank Vector - 4.7 Theorem and Proof for Spectrum of the Google Matrix Chapter 5. Parameters in the PageRank Model: 5.1 The a Factor - 5.2 The Hyperlink Matrix H - 5.3 The Teleportation Matrix E Chapter 6. The Sensitivity of PageRank; 6.1 Sensitivity with respect to alpha - 6.2 Sensitivity with respect to H - 6.3 Sensitivity with respect to vT - 6.4 Other Analyses of Sensitivity - 6.5 Sensitivity Theorems and Proofs Chapter 7. The PageRank Problem as a Linear System: 7.1 Properties of (I - alphaS) - 7.2 Properties of (I - alphaH) - 7.3 Proof of the PageRank Sparse Linear System Chapter 8. Issues in Large-Scale Implementation of PageRank: 8.1 Storage Issues - 8.2 Convergence Criterion - 8.3 Accuracy - 8.4 Dangling Nodes - 8.5 Back Button Modeling
Chapter 9. Accelerating the Computation of PageRank: 9.1 An Adaptive Power Method - 9.2 Extrapolation - 9.3 Aggregation - 9.4 Other Numerical Methods Chapter 10. Updating the PageRank Vector: 10.1 The Two Updating Problems and their History - 10.2 Restarting the Power Method - 10.3 Approximate Updating Using Approximate Aggregation - 10.4 Exact Aggregation - 10.5 Exact vs. Approximate Aggregation - 10.6 Updating with Iterative Aggregation - 10.7 Determining the Partition - 10.8 Conclusions Chapter 11. The HITS Method for Ranking Webpages: 11.1 The HITS Algorithm - 11.2 HITS Implementation - 11.3 HITS Convergence - 11.4 HITS Example - 11.5 Strengths and Weaknesses of HITS - 11.6 HITS's Relationship to Bibliometrics - 11.7 Query-Independent HITS - 11.8 Accelerating HITS - 11.9 HITS Sensitivity Chapter 12. Other Link Methods for Ranking Webpages: 12.1 SALSA - 12.2 Hybrid Ranking Methods - 12.3 Rankings based on Traffic Flow Chapter 13. The Future of Web Information Retrieval: 13.1 Spam - 13.2 Personalization - 13.3 Clustering - 13.4 Intelligent Agents - 13.5 Trends and Time-Sensitive Search - 13.6 Privacy and Censorship - 13.7 Library Classification Schemes - 13.8 Data Fusion Chapter 14. Resources for Web Information Retrieval: 14.1 Resources for Getting Started - 14.2 Resources for Serious Study Chapter 15. The Mathematics Guide: 15.1 Linear Algebra - 15.2 Perron-Frobenius Theory - 15.3 Markov Chains - 15.4 Perron Complementation - 15.5 Stochastic Complementation - 15.6 Censoring - 15.7 Aggregation - 15.8 Disaggregation

0.003699844 = product of:
  0.00924961 = sum of:
    0.006092081 = weight(_text_:a in 616) [ClassicSimilarity], result of:
      0.006092081 = score(doc=616,freq=10.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.11394546 = fieldWeight in 616, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.03125 = fieldNorm(doc=616)
    0.003157529 = product of:
      0.006315058 = sum of:
        0.006315058 = weight(_text_:information in 616) [ClassicSimilarity], result of:
          0.006315058 = score(doc=616,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.0775819 = fieldWeight in 616, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.03125 = fieldNorm(doc=616)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

Purpose - The objective of this paper is to characterize the changes in the rankings of the top ten results of major search engines over time and to compare the rankings between these engines. Design/methodology/approach - The papers compare rankings of the top-ten results of the search engines Google and AlltheWeb on ten identical queries over a period of three weeks. Only the top-ten results were considered, since users do not normally inspect more than the first results page returned by a search engine. The experiment was repeated twice, in October 2003 and in January 2004, in order to assess changes to the top-ten results of some of the queries during the three months interval. In order to assess the changes in the rankings, three measures were computed for each data collection point and each search engine. Findings - The findings in this paper show that the rankings of AlltheWeb were highly stable over each period, while the rankings of Google underwent constant yet minor changes, with occasional major ones. Changes over time can be explained by the dynamic nature of the web or by fluctuations in the search engines' indexes. The top-ten results of the two search engines had surprisingly low overlap. With such small overlap, the task of comparing the rankings of the two engines becomes extremely challenging. Originality/value - The paper shows that because of the abundance of information on the web, ranking search results is of extreme importance. The paper compares several measures for computing the similarity between rankings of search tools, and shows that none of the measures is fully satisfactory as a standalone measure. It also demonstrates the apparent differences in the ranking algorithms of two widely used search engines.

Type

a

0.0035052493 = product of:
  0.008763123 = sum of:
    0.0048162127 = weight(_text_:a in 2572) [ClassicSimilarity], result of:
      0.0048162127 = score(doc=2572,freq=4.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.090081796 = fieldWeight in 2572, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2572)
    0.003946911 = product of:
      0.007893822 = sum of:
        0.007893822 = weight(_text_:information in 2572) [ClassicSimilarity], result of:
          0.007893822 = score(doc=2572,freq=2.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.09697737 = fieldWeight in 2572, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2572)
      0.5 = coord(1/2)
  0.4 = coord(2/5)

Abstract

This paper describes an automatic approach designed to improve the retrieval effectiveness of very short queries such as those used in web searching. The method is based on the observation that stemming, which is designed to maximize recall, often results in depressed precision. Our approach is based on pseudo-feedback and attempts to increase the number of relevant documents in the pseudo-relevant set by reranking those documents based on the presence of unstemmed query terms in the document text. The original experiments underlying this work were carried out using Smart 11.0 and the lnc.ltc weighting scheme on three sets of documents from the TREC collection with corresponding TREC (title only) topics as queries. (The average length of these queries after stoplisting ranges from 2.4 to 4.5 terms.) Results, evaluated in terms of P@20 and non-interpolated average precision, showed clearly that pseudo-feedback (PF) based on this approach was effective in increasing the number of relevant documents in the top ranks. Subsequent experiments, performed on the same data sets using Smart 13.0 and the improved Lnu.ltu weighting scheme, indicate that these results hold up even over the much higher baseline provided by the new weights. Query drift analysis presents a more detailed picture of the improvements produced by this process.

Source

Information processing and management. 38(2002) no.1, S.1-36

Type

a

0.002118135 = product of:
  0.010590675 = sum of:
    0.010590675 = product of:
      0.02118135 = sum of:
        0.02118135 = weight(_text_:information in 4167) [ClassicSimilarity], result of:
          0.02118135 = score(doc=4167,freq=10.0), product of:
            0.08139861 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046368346 = queryNorm
            0.2602176 = fieldWeight in 4167, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=4167)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

This volume contains selected papers that focus on the use of linear algebra, computational statistics, and computer science in the development of algorithms and software systems for text retrieval. Experts in information modeling and retrieval share their perspectives on the design of scalable but precise text retrieval systems, revealing many of the challenges and obstacles that mathematical and statistical models must overcome to be viable for automated text processing. This very useful proceedings is an excellent companion for courses in information retrieval, applied linear algebra, and applied statistics. Computational Information Retrieval provides background material on vector space models for text retrieval that applied mathematicians, statisticians, and computer scientists may not be familiar with. For graduate students in these areas, several research questions in information modeling are exposed. In addition, several case studies concerning the efficacy of the popular Latent Semantic Analysis (or Indexing) approach are provided.

0.002043346 = product of:
  0.01021673 = sum of:
    0.01021673 = weight(_text_:a in 751) [ClassicSimilarity], result of:
      0.01021673 = score(doc=751,freq=18.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.19109234 = fieldWeight in 751, 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=751)
  0.2 = coord(1/5)

Abstract

Purpose - The purpose of this paper is to suggest an alternative to the widely used Times Cited criterion for analysing citation networks. The approach involves taking account of the natures of the papers that cite a given paper, so as to differentiate between papers that attract the same number of citations. Design/methodology/approach - ArticleRank is an algorithm that has been derived from Google's PageRank algorithm to measure the influence of journal articles. ArticleRank is applied to two datasets - a citation network based on an early paper on webometrics, and a self-citation network based on the 19 most cited papers in the Journal of Documentation - using citation data taken from the Web of Knowledge database. Findings - ArticleRank values provide a different ranking of a set of papers from that provided by the corresponding Times Cited values, and overcomes the inability of the latter to differentiate between papers with the same numbers of citations. The difference in rankings between Times Cited and ArticleRank is greatest for the most heavily cited articles in a dataset. Originality/value - This is a novel application of the PageRank algorithm.

Type

a

0.0019264851 = product of:
  0.009632425 = sum of:
    0.009632425 = weight(_text_:a in 4422) [ClassicSimilarity], result of:
      0.009632425 = score(doc=4422,freq=4.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.18016359 = fieldWeight in 4422, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.078125 = fieldNorm(doc=4422)
  0.2 = coord(1/5)

Abstract

Robertson comments on the theoretical status of IDF term weighting. Its history illustrates how ideas develop in a specific research context, in theory/experiment interaction, and in operational practice.

Type

a

0.0019071229 = product of:
  0.009535614 = sum of:
    0.009535614 = weight(_text_:a in 3662) [ClassicSimilarity], result of:
      0.009535614 = score(doc=3662,freq=2.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.17835285 = fieldWeight in 3662, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.109375 = fieldNorm(doc=3662)
  0.2 = coord(1/5)

Type

a

0.0019071229 = product of:
  0.009535614 = sum of:
    0.009535614 = weight(_text_:a in 4797) [ClassicSimilarity], result of:
      0.009535614 = score(doc=4797,freq=2.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.17835285 = fieldWeight in 4797, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.109375 = fieldNorm(doc=4797)
  0.2 = coord(1/5)

Type

a

0.001651617 = product of:
  0.008258085 = sum of:
    0.008258085 = weight(_text_:a in 4420) [ClassicSimilarity], result of:
      0.008258085 = score(doc=4420,freq=6.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.1544581 = fieldWeight in 4420, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0546875 = fieldNorm(doc=4420)
  0.2 = coord(1/5)

Abstract

The exhaustivity of document descriptions and the specificity of index terms are usually regarded as independent. It is suggested that specificity should be interpreted statistically, as a function of term use rather than of term meaning. The effects on retrieval of variations in term specificity are examined, experiments with three test collections showing, in particular, that frequently-occurring terms are required for good overall performance. It is argued that terms should be weighted according to collection frequency, so that matches on less frequent, more specific, terms are of greater value than matches on frequent terms. Results for the test collections show that considerable improvements in performance are obtained with this very simple procedure.

Type

a

0.0015230201 = product of:
  0.0076151006 = sum of:
    0.0076151006 = weight(_text_:a in 2810) [ClassicSimilarity], result of:
      0.0076151006 = score(doc=2810,freq=10.0), product of:
        0.053464882 = queryWeight, product of:
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.046368346 = queryNorm
        0.14243183 = fieldWeight in 2810, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.153047 = idf(docFreq=37942, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2810)
  0.2 = coord(1/5)

Abstract

Some Online Public Access Catalogues offer a ranking component. However, ranking there is merely text-based and is doomed to fail due to limited text in bibliographic data. The main assumption for the talk is that we are in a situation where the appropriate ranking factors for OPACs should be defined, while the implementation is no major problem. We must define what we want, and not so much focus on the technical work. Some deep thinking is necessary on the "perfect results set" and how we can achieve it through ranking. The talk presents a set of potential ranking factors and clustering possibilities for further discussion. A look at commercial Web search engines could provide us with ideas how ranking can be improved with additional factors. Search engines are way beyond pure text-based ranking and apply ranking factors in the groups like popularity, freshness, personalisation, etc. The talk describes the main factors used in search engines and how derivatives of these could be used for libraries' purposes. The goal of ranking is to provide the user with the best-suitable results on top of the results list. How can this goal be achieved with the library catalogue and also concerning the library's different collections and databases? The assumption is that ranking of such materials is a complex problem and is yet nowhere near solved. Libraries should focus on ranking to improve user experience.