• Publications
  • Influence
Sentiment strength detection for the social web
An improved version of the algorithm SentiStrength for sentiment strength detection across the social web that primarily uses direct indications of sentiment is assessed, suggesting that, even unsupervised, Senti strength is robust enough to be applied to a wide variety of different social web contexts. Expand
Sentiment in short strength detection informal text
A new algorithm is partly filled with a new algorithm, SentiStrength, to extract sentiment strength from informal English text, using new methods to exploit the de facto grammars and spelling styles of cyberspace. Expand
The metric tide: report of the independent review of the role of metrics in research assessment and management
This report presents the findings and recommendations of the Independent Review of the Role of Metrics in Research Assessment and Management. The review was chaired by Professor James Wilsdon,Expand
Do Altmetrics Work? Twitter and Ten Other Social Web Services
Comparisons between citations and metric values for articles published at different times, even within the same year, can remove or reverse this association and so publishers and scientometricians should consider the effect of time when using altmetrics to rank articles. Expand
Sentiment in Twitter events
A study of a month of English Twitter posts is reported, assessing whether popular events are typically associated with increases in sentiment strength, as seems intuitively likely and using the top 30 events as a measure of relative increase in (general) term usage. Expand
Sentiment analysis: A combined approach
This paper combines rule-based classification, supervised learning and machine learning into a new combined method, and proposes a semi-automatic, complementary approach in which each classifier can contribute to other classifiers to achieve a good level of effectiveness. Expand
A Study of Information Retrieval Weighting Schemes for Sentiment Analysis
It is shown that variants of the classic tf.idf scheme adapted to sentiment analysis provide significant increases in accuracy, especially when using a sublinear function for term frequency weights and document frequency smoothing. Expand
Tweeting biomedicine: An analysis of tweets and citations in the biomedical literature
This article aims to provide systematic evidence about how often Twitter is used to disseminate information about journal articles in the biomedical sciences by evaluating the degree to which certain journals, disciplines, and specialties were represented on Twitter and how far tweets correlate with citation impact. Expand
Validating online reference managers for scholarly impact measurement
This paper investigates whether CiteULike and Mendeley are useful for measuring scholarly influence, using a sample of 1,613 papers published in Nature and Science in 2007. Traditional citationExpand