English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the proliferation of its applications in various industries, sentimentanalysis by using publicly available web data has become an active researcharea in text classification during these years. It is argued by researchersthat semi-supervised learning is an effective approach to this problem since itis capable to mitigate the manual labeling effort which is usually expensiveand time-consuming. However, there was a long-term debate on the effectivenessof unlabeled data in text classification. This was partially caused by the factthat many assumptions in theoretic analysis often do not hold in practice. Weargue that this problem may be further understood by adding an additionaldimension in the experiment. This allows us to address this problem in theperspective of bias and variance in a broader view. We show that the well-knownperformance degradation issue caused by unlabeled data can be reproduced as asubset of the whole scenario. We argue that if the bias-variance trade-off isto be better balanced by a more effective feature selection method unlabeleddata is very likely to boost the classification performance. We then propose afeature selection framework in which labeled and unlabeled training samples areboth considered. We discuss its potential in achieving such a balance. Besides,the application in financial sentiment analysis is chosen because it not onlyexemplifies an important application, the data possesses better illustrativepower as well. The implications of this study in text classification andfinancial sentiment analysis are both discussed.

Exploring The Contribution of Unlabeled Data in Financial Sentiment Analysis