Learn More
Sentiment analysis is concerned with the automatic extraction of sentiment-related information from text. Although most sentiment analysis addresses commercial tasks, such as extracting opinions from product reviews, there is increasing interest in the affective dimension of the social web, and Twitter in particular. Most sentiment analysis algorithms are(More)
Most sentiment analysis approaches use as baseline a support vector machines (SVM) classifier with binary unigram weights. In this paper, we explore whether more sophisticated feature weighting schemes from Information Retrieval can enhance classification accuracy. We show that variants of the classic tf.idf scheme adapted to sentiment analysis provide(More)
Data collected by social media platforms have recently been introduced as a new source for indicators to help measure the impact of scholarly research in ways that are complementary to traditional citation-based indicators. Data generated from social media activities related to scholarly content can be used to reflect broad types of impact. This paper aims(More)
Altmetric measurements derived from the social web are increasingly advocated and used as early indicators of article impact and usefulness. Nevertheless, there is a lack of systematic scientific evidence that altmetrics are valid proxies of either impact or utility although a few case studies have reported medium correlations between specific altmetrics(More)
BACKGROUND Citations in peer-reviewed articles and the impact factor are generally accepted measures of scientific impact. Web 2.0 tools such as Twitter, blogs or social bookmarking tools provide the possibility to construct innovative article-level or journal-level metrics to gauge impact and influence. However, the relationship of the these new metrics to(More)
Much has been written about the potential and pitfalls of macroscopic web-based link analysis, yet there have been no studies that have provided clear statistical evidence that any of the proposed calculations can produce results over large areas of the web that correlate with phenomena external to the Internet. This article attempts to provide such(More)
The web is an important medium for scholarly communication of various types, perhaps eventually to entirely replace some traditional mechanisms such as print journals. Yet the web analogy of citations, hyperlinks, are much more varied in use and existing citation techniques are difficult to generalise to the new medium. In this context, one new challenging(More)