Search (5 results, page 1 of 1)

  • × year_i:[2010 TO 2020}
  • × author_ss:"Liu, X."
  1. Liu, X.; Yu, S.; Janssens, F.; Glänzel, W.; Moreau, Y.; Moor, B.de: Weighted hybrid clustering by combining text mining and bibliometrics on a large-scale journal database (2010) 0.01
    0.009195855 = product of:
      0.01839171 = sum of:
        0.01839171 = product of:
          0.03678342 = sum of:
            0.03678342 = weight(_text_:web in 3464) [ClassicSimilarity], result of:
              0.03678342 = score(doc=3464,freq=2.0), product of:
                0.17002425 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.052098576 = queryNorm
                0.21634221 = fieldWeight in 3464, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.046875 = fieldNorm(doc=3464)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    We propose a new hybrid clustering framework to incorporate text mining with bibliometrics in journal set analysis. The framework integrates two different approaches: clustering ensemble and kernel-fusion clustering. To improve the flexibility and the efficiency of processing large-scale data, we propose an information-based weighting scheme to leverage the effect of multiple data sources in hybrid clustering. Three different algorithms are extended by the proposed weighting scheme and they are employed on a large journal set retrieved from the Web of Science (WoS) database. The clustering performance of the proposed algorithms is systematically evaluated using multiple evaluation methods, and they were cross-compared with alternative methods. Experimental results demonstrate that the proposed weighted hybrid clustering strategy is superior to other methods in clustering performance and efficiency. The proposed approach also provides a more refined structural mapping of journal sets, which is useful for monitoring and detecting new trends in different scientific fields.
  2. Liu, X.; Turtle, H.: Real-time user interest modeling for real-time ranking (2013) 0.01
    0.009195855 = product of:
      0.01839171 = sum of:
        0.01839171 = product of:
          0.03678342 = sum of:
            0.03678342 = weight(_text_:web in 1035) [ClassicSimilarity], result of:
              0.03678342 = score(doc=1035,freq=2.0), product of:
                0.17002425 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.052098576 = queryNorm
                0.21634221 = fieldWeight in 1035, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.046875 = fieldNorm(doc=1035)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    User interest as a very dynamic information need is often ignored in most existing information retrieval systems. In this research, we present the results of experiments designed to evaluate the performance of a real-time interest model (RIM) that attempts to identify the dynamic and changing query level interests regarding social media outputs. Unlike most existing ranking methods, our ranking approach targets calculation of the probability that user interest in the content of the document is subject to very dynamic user interest change. We describe 2 formulations of the model (real-time interest vector space and real-time interest language model) stemming from classical relevance ranking methods and develop a novel methodology for evaluating the performance of RIM using Amazon Mechanical Turk to collect (interest-based) relevance judgments on a daily basis. Our results show that the model usually, although not always, performs better than baseline results obtained from commercial web search engines. We identify factors that affect RIM performance and outline plans for future research.
  3. Liu, X.; Guo, C.; Zhang, L.: Scholar metadata and knowledge generation with human and artificial intelligence (2014) 0.01
    0.009195855 = product of:
      0.01839171 = sum of:
        0.01839171 = product of:
          0.03678342 = sum of:
            0.03678342 = weight(_text_:web in 1287) [ClassicSimilarity], result of:
              0.03678342 = score(doc=1287,freq=2.0), product of:
                0.17002425 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.052098576 = queryNorm
                0.21634221 = fieldWeight in 1287, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.046875 = fieldNorm(doc=1287)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    Scholar metadata have traditionally centered on descriptive representations, which have been used as a foundation for scholarly publication repositories and academic information retrieval systems. In this article, we propose innovative and economic methods of generating knowledge-based structural metadata (structural keywords) using a combination of natural language processing-based machine-learning techniques and human intelligence. By allowing low-barrier participation through a social media system, scholars (both as authors and users) can participate in the metadata editing and enhancing process and benefit from more accurate and effective information retrieval. Our experimental web system ScholarWiki uses machine learning techniques, which automatically produce increasingly refined metadata by learning from the structural metadata contributed by scholars. The cumulated structural metadata add intelligence and automatically enhance and update recursively the quality of metadata, wiki pages, and the machine-learning model.
  4. Clewley, N.; Chen, S.Y.; Liu, X.: Cognitive styles and search engine preferences : field dependence/independence vs holism/serialism (2010) 0.01
    0.007663213 = product of:
      0.015326426 = sum of:
        0.015326426 = product of:
          0.030652853 = sum of:
            0.030652853 = weight(_text_:web in 3961) [ClassicSimilarity], result of:
              0.030652853 = score(doc=3961,freq=2.0), product of:
                0.17002425 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.052098576 = queryNorm
                0.18028519 = fieldWeight in 3961, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=3961)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    Purpose - Cognitive style has been identified to be significantly influential in deciding users' preferences of search engines. In particular, Witkin's field dependence/independence has been widely studied in the area of web searching. It has been suggested that this cognitive style has conceptual links with the holism/serialism. This study aims to investigate the differences between the field dependence/independence and holism/serialism. Design/methodology/approach - An empirical study was conducted with 120 students from a UK university. Riding's cognitive style analysis (CSA) and Ford's study preference questionnaire (SPQ) were used to identify the students' cognitive styles. A questionnaire was designed to identify users' preferences for the design of search engines. Data mining techniques were applied to analyse the data obtained from the empirical study. Findings - The results highlight three findings. First, a fundamental link is confirmed between the two cognitive styles. Second, the relationship between field dependent users and holists is suggested to be more prominent than that of field independent users and serialists. Third, the interface design preferences of field dependent and field independent users can be split more clearly than those of holists and serialists. Originality/value - The contributions of this study include a deeper understanding of the similarities and differences between field dependence/independence and holists/serialists as well as proposing a novel methodology for data analyses.
  5. Chen, Z.; Huang, Y.; Tian, J.; Liu, X.; Fu, K.; Huang, T.: Joint model for subsentence-level sentiment analysis with Markov logic (2015) 0.01
    0.007663213 = product of:
      0.015326426 = sum of:
        0.015326426 = product of:
          0.030652853 = sum of:
            0.030652853 = weight(_text_:web in 2210) [ClassicSimilarity], result of:
              0.030652853 = score(doc=2210,freq=2.0), product of:
                0.17002425 = queryWeight, product of:
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.052098576 = queryNorm
                0.18028519 = fieldWeight in 2210, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.2635105 = idf(docFreq=4597, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=2210)
          0.5 = coord(1/2)
      0.5 = coord(1/2)
    
    Abstract
    Sentiment analysis mainly focuses on the study of one's opinions that express positive or negative sentiments. With the explosive growth of web documents, sentiment analysis is becoming a hot topic in both academic research and system design. Fine-grained sentiment analysis is traditionally solved as a 2-step strategy, which results in cascade errors. Although joint models, such as joint sentiment/topic and maximum entropy (MaxEnt)/latent Dirichlet allocation, are proposed to tackle this problem of sentiment analysis, they focus on the joint learning of both aspects and sentiments. Thus, they are not appropriate to solve the cascade errors for sentiment analysis at the sentence or subsentence level. In this article, we present a novel jointly fine-grained sentiment analysis framework at the subsentence level with Markov logic. First, we divide the task into 2 separate stages (subjectivity classification and polarity classification). Then, the 2 separate stages are processed, respectively, with different feature sets, which are implemented by local formulas in Markov logic. Finally, global formulas in Markov logic are adopted to realize the interactions of the 2 separate stages. The joint inference of subjectivity and polarity helps prevent cascade errors. Experiments on a Chinese sentiment data set manifest that our joint model brings significant improvements.