To understand narrative text, we must comprehend how people are affected by the events that they experience. For example, readers understand that graduating from college is a positive event (achievement) but being fired from one's job is a negative event (problem). NLP researchers have developed effective tools for recognizing explicit sentiments, but affective events are more difficult to recognize because the polarity is often implicit and can depend on both a predicate and its arguments. Our research investigates the prevalence of affective events in a personal story corpus, and introduces a weakly supervised method for large scale induction of affective events. We present an iterative learning framework that constructs a graph with nodes representing events and initializes their affective polarities with sentiment analysis tools as weak supervision. The events are then linked based on three types of semantic relations: (1) semantic similarity, (2) semantic opposition, and (3) shared components. The learning algorithm iteratively refines the polarity values by optimizing semantic consistency across all events in the graph. Our model learns over 100,000 affective events and identifies their polarities more accurately than other methods.
The epithelial-mesenchymal transition occurs when epithelial cells lose apicobasal polarity and cell-cell contacts and migrate into surrounding tissues as mesenchymal cells. Migration is crucial for gastrulation, neural tube formation, and cancer metastasis. However, the mechanisms underlying loss of polarity and cell movement are poorly understood. The change in cell organization results in the transition from apicobasal polarity to front-rear polarity that precedes cell migration. Micropatterned cell culture showed that the mechanism is cell-intrinsic and governed by microtubule reorganization but is not influenced by neighboring cells.
Reis, Julio Cesar Soares dos (Federal University of Minas Gerais) | Gonçalves, Pollyanna (Federal University of Minas Gerais) | Olmo, Pedro (Federal University of Minas Gerais) | Prates, Raquel (Federal University of Minas Gerais) | Benevenuto, Fabrício (Federal University of Minas Gerais)
When was the last time you read a newspaper and was bombarded with articles you would rather not see? Current news media shows massive number of news every day. But from tragedies to happy stories, people might want to choose to read only those articles that fit their current mood. The purpose of this project is to present the Magnet News , a Web tool in which users can choose if they want to see positive or negative news. Our system monitors the sentiment of news from important newspapers using the SentiStrength, a sentiment method proposed by literature that has been proved to be efficient in previous analysis.
The properties of plastics can often benefit from the use of a mix of polar and nonpolar building blocks in their preparation. However, these different building blocks may be chemically incompatible or vary substantially in their solubility and reactivity, complicating synthetic planning. Van de Wouw et al. used boron and nitrogen to endow a nonpolar monomer with latent prospects for polarization. The BN aromatic was easily copolymerized with styrene. Peroxide treatment then replaced the dangling boron-bearing ring with a hydroxyl group that would have been challenging to introduce evenly at the outset.
This paper focusses on the main issues related to the development of a corpus for opinion and sentiment analysis, with a special attention to irony, and presents as a case study Senti-TUT, a project for Italian aimed at investigating sentiment and irony in social media. We present the Senti-TUT corpus, a collection of texts from Twitter annotated with sentiment polarity. We describe the dataset, the annotation, the methodologies applied and our investigations on two important features of irony: polarity reversing and emotion expressions.