Search (6 results, page 1 of 1)

0.019060206 = product of:
  0.03812041 = sum of:
    0.03812041 = sum of:
      0.01008212 = weight(_text_:a in 3293) [ClassicSimilarity], result of:
        0.01008212 = score(doc=3293,freq=22.0), product of:
          0.04772363 = queryWeight, product of:
            1.153047 = idf(docFreq=37942, maxDocs=44218)
            0.041389145 = queryNorm
          0.21126054 = fieldWeight in 3293, 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=3293)
      0.028038291 = weight(_text_:22 in 3293) [ClassicSimilarity], result of:
        0.028038291 = score(doc=3293,freq=2.0), product of:
          0.14493774 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.041389145 = queryNorm
          0.19345059 = fieldWeight in 3293, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0390625 = fieldNorm(doc=3293)
  0.5 = coord(1/2)

Abstract

For projects in knowledge-intensive domains, it is crucially important that knowledge management systems are able to track and infer workers' up-to-date information needs so that task-relevant information can be delivered in a timely manner. To put a worker's dynamic information needs into perspective, we propose a topic variation inspection model to facilitate the application of an implicit relevance feedback (IRF) algorithm and collaborative filtering in user modeling. The model analyzes variations in a worker's task-needs for a topic (i.e., personal topic needs) over time, monitors changes in the topics of collaborative actors, and then adjusts the worker's profile accordingly. We conducted a number of experiments to evaluate the efficacy of the model in terms of precision, recall, and F-measure. The results suggest that the proposed collaborative topic variation inspection approach can substantially improve the performance of a basic profiling method adapted from the classical RF algorithm. It can also improve the accuracy of other methods when a worker's information needs are vague or evolving, i.e., when there is a high degree of variation in the worker's topic-needs. Our findings have implications for the design of an effective collaborative information filtering and retrieval model, which is crucial for reusing an organization's knowledge assets effectively.

Date

2. 2.2010 19:22:51

Type

a

0.016168661 = product of:
  0.032337323 = sum of:
    0.032337323 = sum of:
      0.00429903 = weight(_text_:a in 4573) [ClassicSimilarity], result of:
        0.00429903 = score(doc=4573,freq=4.0), product of:
          0.04772363 = queryWeight, product of:
            1.153047 = idf(docFreq=37942, maxDocs=44218)
            0.041389145 = queryNorm
          0.090081796 = fieldWeight in 4573, 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=4573)
      0.028038291 = weight(_text_:22 in 4573) [ClassicSimilarity], result of:
        0.028038291 = score(doc=4573,freq=2.0), product of:
          0.14493774 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.041389145 = queryNorm
          0.19345059 = fieldWeight in 4573, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0390625 = fieldNorm(doc=4573)
  0.5 = coord(1/2)

Abstract

This study explores how user subject knowledge influences search task processes and outcomes, as well as how search behavior is influenced by subject-oriented information visualization (IV) tools. To enable integrated searches, the proposed WikiMap + integrates search functions and IV tools (i.e., a topic network and hierarchical topic tree) and gathers information from Wikipedia pages and Google Search results. To evaluate the effectiveness of the proposed interfaces, we design subject-oriented tasks and adopt extended evaluation measures. We recruited 48 novices and 48 knowledgeable users, that is, intermediates, for the evaluation. Our results show that novices using the proposed interface demonstrate better search performance than intermediates using Wikipedia. We therefore conclude that our tools help close the gap between novices and intermediates in information searches. The results also show that intermediates can take advantage of the search tool by leveraging the IV tools to browse subtopics, and formulate better queries with less effort. We conclude that embedding the IV and the search tools in the interface can result in different search behavior but improved task performance. We provide implications to design search systems to include IV features adapted to user levels of subject knowledge to help them achieve better task performance.

Date

9.12.2018 16:22:25

Type

a

0.002740105 = product of:
  0.00548021 = sum of:
    0.00548021 = product of:
      0.01096042 = sum of:
        0.01096042 = weight(_text_:a in 2115) [ClassicSimilarity], result of:
          0.01096042 = score(doc=2115,freq=26.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.22966442 = fieldWeight in 2115, product of:
              5.0990195 = tf(freq=26.0), with freq of:
                26.0 = termFreq=26.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2115)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Effective knowledge management in a knowledge-intensive environment can place heavy demands on the information filtering (IF) strategies used to model workers' long-term task-needs. Because of the growing complexity of knowledge-intensive work tasks, a profiling technique is needed to deliver task-relevant documents to workers. In this study, we propose an IF technique with task-stage identification that provides effective codification-based support throughout the execution of a task. Task-needs pattern similarity analysis based on a correlation value is used to identify a worker's task-stage (the pre-focus, focus formulation, or post-focus task-stage). The identified task-stage is then incorporated into a profile adaptation process to generate the worker's current task profile. The results of a pilot study conducted in a research institute confirm that there is a low or negative correlation between search sessions and transactions in the pre-focus task-stage, whereas there is at least a moderate correlation between search sessions/transactions in the post-focus stage. Compared with the traditional IF technique, the proposed IF technique with task-stage identification achieves, on average, a 19.49% improvement in task-relevant document support. The results confirm the effectiveness of the proposed method for knowledge-intensive work tasks.

Type

a

0.0019225847 = product of:
  0.0038451694 = sum of:
    0.0038451694 = product of:
      0.007690339 = sum of:
        0.007690339 = weight(_text_:a in 1797) [ClassicSimilarity], result of:
          0.007690339 = score(doc=1797,freq=20.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.16114321 = fieldWeight in 1797, 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=1797)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Purpose - The authors introduce two semantics-based navigation applications that facilitate information-seeking activities in internal link-based web sites in Wikipedia. These applications aim to help users find concepts within a topic and related articles on a given topic quickly and then gain topical knowledge from internal link-based encyclopedia web sites. The paper aims to discuss these issues. Design/methodology/approach - The WNavis application consists of three information visualization (IV) tools which are a topic network, a hierarchy topic tree and summaries for topics. The WikiMap application consists of a topic network. The goal of the topic network and topic tree tools is to help users to find the major concepts of a topic and identify relationships between these major concepts easily. In addition, in order to locate specific information and enable users to explore and read topic-related articles quickly, the topic tree and summaries for topics tools support users to gain topical knowledge quickly. The authors then apply the k-clique of cohesive indicator to analyze the sub topics of the seed query and find out the best clustering results via the cosine measure. The authors utilize four metrics, which are correctness, time cost, usage behaviors, and satisfaction, to evaluate the three interfaces. These metrics measure both the outputs and outcomes of applications. As a baseline system for evaluation the authors used a traditional Wikipedia interface. For the evaluation, the authors used an experimental user study with 30 participants.
Findings - The results indicate that both WikiMap and WNavis supported users to identify concepts and their relations better compared to the baseline. In topical tasks WNavis over performed both WikiMap and the baseline system. Although there were no time differences in finding concepts or answering topical questions, the test systems provided users with a greater gain per time unit. The users of WNavis leaned on the hierarchy tree instead of other tools, whereas WikiMap users used the topic map. Research limitations/implications - The findings have implications for the design of IR support tools in knowledge-intensive web sites that help users to explore topics and concepts. Originality/value - The authors explored to what extent the use of each IV support tool contributed to successful exploration of topics in search tasks. The authors propose extended task-based evaluation measures to understand how each application provides useful context for users to accomplish the tasks and attain the search goals. That is, the authors not only evaluate the output of the search results, e.g. the number of relevant items retrieved, but also the outcome provided by the system for assisting users to attain the search goal.

Type

a

0.0015199365 = product of:
  0.003039873 = sum of:
    0.003039873 = product of:
      0.006079746 = sum of:
        0.006079746 = weight(_text_:a in 2130) [ClassicSimilarity], result of:
          0.006079746 = score(doc=2130,freq=8.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.12739488 = fieldWeight in 2130, 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=2130)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This study explores how the stability of users' preferences influences recommendation results and how this stability relates to the effectiveness of developing recommendation strategies. In this work, we propose an anchor-based hybrid filtering approach (AHF) to naturally measure and capture the user's preference stabilities for movie genres. That is, a pairwise preference of the genre comparison process with the genre-based fuzzy inference filtering was conducted in order to achieve effective interactive recommendations. To conduct this experiment, we recruited 30 users with different levels of preference stability for movie genres. The experimental results show that the proposed AHF approach can effectively capture the user's preferences and filter out undesired movie genres. In addition, this approach can give a more precise recommendation than one without the anchoring process, especially for the user who has unstable preferences for movie genres. Our proposed approach achieves statistical significance and outperforms the baseline method for recommending users' favorite movies by more than 63% for the stable user group and 77% for the unstable group. The results suggest that the stability of users' preferences is a factor to be considered when developing effective recommendation strategies.

Type

a

0.0012159493 = product of:
  0.0024318986 = sum of:
    0.0024318986 = product of:
      0.004863797 = sum of:
        0.004863797 = weight(_text_:a in 4545) [ClassicSimilarity], result of:
          0.004863797 = score(doc=4545,freq=8.0), product of:
            0.04772363 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.041389145 = queryNorm
            0.10191591 = fieldWeight in 4545, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.03125 = fieldNorm(doc=4545)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Purpose - Seeking and retrieving information is an essential aspect of knowledge workers' activities during problem-solving and decision-making tasks. In recent years, user-oriented Information Seeking (IS) research methods rooted in the social sciences have been integrated with Information Retrieval (IR) research approaches based on computer science to capitalize on the strengths of each field. Given this background, the objective is to develop a topic-needs variation determination technique based on the observations of IS&R theories. Design/methodology/approach - In this study, implicit and explicit methods for identifying users' evolving topic-needs are proposed. Knowledge-intensive tasks performed by academic researchers are used to evaluate the efficacy of the proposed methods. The paper conducted two sets of experiments to demonstrate and verify the importance of determining changes in topic-needs during the IS&R process. Findings - The results in terms of precision and discounted cumulated gain (DCG) values show that the proposed Stage-Topic_W (G,S) and Stage-Topic-Interaction methods can retrieve relevant document sets for users engaged in long-term tasks more efficiently and effectively than traditional methods. Practical implications - The improved precision of the proposed methods means that they can retrieve more relevant documents for the searcher. Accordingly, the results of this research have implications for enhancing the search function in enterprise content management (ECM) applications to support the execution of projects/tasks by professionals and facilitate effective ECM. Originality/value - The model observes a user's search behavior pattern to determine the personal factors (e.g. changes in the user's cognitive status), and content factors (e.g. changes in topic-needs) simultaneously. The objective is to capture changes in the user's information needs precisely so that evolving information needs can be satisfied in a timely manner.

Type

a