Search (2 results, page 1 of 1)

  • × author_ss:"Zeng, D."
  1. Chung, W.; Zeng, D.: Social-media-based public policy informatics : sentiment and network analyses of U.S. immigration and border security (2016) 0.02 
    0.01988719 = product of:
  0.03977438 = sum of:
    0.008155267 = product of:
      0.032621067 = sum of:
        0.032621067 = weight(_text_:based in 3969) [ClassicSimilarity], result of:
          0.032621067 = score(doc=3969,freq=6.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.2306343 = fieldWeight in 3969, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.03125 = fieldNorm(doc=3969)
      0.25 = coord(1/4)
    0.031619113 = product of:
      0.063238226 = sum of:
        0.063238226 = weight(_text_:assessment in 3969) [ClassicSimilarity], result of:
          0.063238226 = score(doc=3969,freq=2.0), product of:
            0.25917634 = queryWeight, product of:
              5.52102 = idf(docFreq=480, maxDocs=44218)
              0.04694356 = queryNorm
            0.2439969 = fieldWeight in 3969, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.52102 = idf(docFreq=480, maxDocs=44218)
              0.03125 = fieldNorm(doc=3969)
      0.5 = coord(1/2)
  0.5 = coord(2/4)
    Abstract
    Social media provide opportunities for policy makers to gauge pubic opinion. However, the large volumes and variety of expressions on social media have challenged traditional policy analysis and public sentiment assessment. In this article, we describe a framework for social-media-based public policy informatics and a system called "iMood" that addresses the needs for sentiment and network analyses of U.S. immigration and border security. iMood collects related messages on Twitter, extracts user sentiment and emotion, and constructs networks of the Twitter users, helping policy makers to identify opinion leaders, influential users, and community activists. We evaluated the sentiment, emotion, and network characteristics found in 909,035 tweets posted by over 300,000 users during three phases between May and November 2013. Statistical analyses reveal significant differences in emotion and sentiment among the 3 phases. The Twitter networks of the 3 phases also had significantly different relationship counts, network densities, and total influence scores from those of other phases. This research should contribute to developing a new framework and a new system for social-media-based public policy informatics, providing new empirical findings and data sets of sentiment and network analyses of U.S. immigration and border security, and demonstrating a general applicability to different domains.
  2. Zhang, C.; Zeng, D.; Li, J.; Wang, F.-Y.; Zuo, W.: Sentiment analysis of Chinese documents : from sentence to document level (2009) 0.00 
    0.0035313342 = product of:
  0.014125337 = sum of:
    0.014125337 = product of:
      0.056501348 = sum of:
        0.056501348 = weight(_text_:based in 3296) [ClassicSimilarity], result of:
          0.056501348 = score(doc=3296,freq=8.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.39947033 = fieldWeight in 3296, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.046875 = fieldNorm(doc=3296)
      0.25 = coord(1/4)
  0.25 = coord(1/4)
    Abstract
    User-generated content on the Web has become an extremely valuable source for mining and analyzing user opinions on any topic. Recent years have seen an increasing body of work investigating methods to recognize favorable and unfavorable sentiments toward specific subjects from online text. However, most of these efforts focus on English and there have been very few studies on sentiment analysis of Chinese content. This paper aims to address the unique challenges posed by Chinese sentiment analysis. We propose a rule-based approach including two phases: (1) determining each sentence's sentiment based on word dependency, and (2) aggregating sentences to predict the document sentiment. We report the results of an experimental study comparing our approach with three machine learning-based approaches using two sets of Chinese articles. These results illustrate the effectiveness of our proposed method and its advantages against learning-based approaches.

Authors

Years