Sentiment composition
K Moilanen, S Pulman - International Conference Recent Advances in …, 2007 - ora.ox.ac.uk
Sentiment classification of grammatical constituents can be explained in a
quasicompositional way. The classification of a complex constituent is derived via the …
quasicompositional way. The classification of a complex constituent is derived via the …
Tweets about hospital quality: a mixed methods study
F Greaves, AA Laverty, DR Cano… - BMJ quality & …, 2014 - qualitysafety.bmj.com
Background Twitter is increasingly being used by patients to comment on their experience of
healthcare. This may provide information for understanding the quality of healthcare …
healthcare. This may provide information for understanding the quality of healthcare …
[PDF][PDF] Predicting economic indicators from web text using sentiment composition
A Levenberg, S Pulman, K Moilanen… - International Journal of …, 2014 - academia.edu
Of late there has been a significant amount of work on using sources of text data from the
Web (such as Twitter or Google Trends) to predict financial and economic variables of …
Web (such as Twitter or Google Trends) to predict financial and economic variables of …
Leveraging textual sentiment analysis with social network modelling
W Gryc, K Moilanen - From Text to Political Positions: Text …, 2014 - books.google.com
Automatic computational analysis of political texts poses major challenges for state-of-the-art
Sentiment Analysis and Natural Language Processing tools. In this initial study, we …
Sentiment Analysis and Natural Language Processing tools. In this initial study, we …
Knowledge-aware leap-lstm: Integrating prior knowledge into leap-lstm towards faster long text classification
While widely used in industry, recurrent neural networks (RNNs) are known to have
deficiencies in dealing with long sequences (eg slow inference, vanishing gradients etc.) …
deficiencies in dealing with long sequences (eg slow inference, vanishing gradients etc.) …
[PDF][PDF] Packed feelings and ordered sentiments: Sentiment parsing with quasi-compositional polarity sequencing and compression
Recent solutions proposed for sentence-and phrase-level sentiment analysis have reflected
a variety of analytical and computational paradigms that include anything from naıve …
a variety of analytical and computational paradigms that include anything from naıve …
The Good ‚the Bad ‚and the Unknown: Morphosyllabic Sentiment Tagging of Unseen Words
K Moilanen, S Pulman - 2015 - ora.ox.ac.uk
The omnipresence of unknown words is a problem that any NLP component needs to
address in some form. While there exist many established techniques for dealing with …
address in some form. While there exist many established techniques for dealing with …
Pointing to select: A fast pointer-LSTM for long text classification
Recurrent neural networks (RNNs) suffer from well-known limitations and complications
which include slow inference and vanishing gradients when processing long sequences in …
which include slow inference and vanishing gradients when processing long sequences in …
[PDF][PDF] Multi-entity sentiment scoring
K Moilanen, S Pulman - Proceedings of the International …, 2009 - aclanthology.org
We present a compositional framework for modelling entity-level sentiment (sub) contexts,
and demonstrate how holistic multi-entity polarity scoring emerges as a by-product of …
and demonstrate how holistic multi-entity polarity scoring emerges as a by-product of …
Persuasive dialogue based on a narrative theory: An eca implementation
Abstract Embodied Conversational Agents (ECA) are poised to constitute a specific category
within persuasive systems, in particular through their ability to support affective dialogue …
within persuasive systems, in particular through their ability to support affective dialogue …