Event extraction using behaviors of sentiment signals and burst structure in social media

Significant world events often cause the behavioral convergence of the expression of shared sentiment. This paper examines the use of the blogosphere as a framework to study user psychological behaviors, using their sentiment responses as a form of ‘sensor’ to infer real-world events of importance automatically. We formulate a novel temporal sentiment index function using quantitative measure of the valence value of bearing words in blog posts in which the set of affective bearing words is inspired from psychological research in emotion structure. The annual local minimum and maximum of the proposed sentiment signal function are utilized to extract significant events of the year and corresponding blog posts are further analyzed using topic modeling tools to understand their content. The paper then examines the correlation of topics discovered in relation to world news events reported by the mainstream news service provider, Cable News Network, and by using the Google search engine. Next, aiming at understanding sentiment at a finer granularity over time, we propose a stochastic burst detection model, extended from the work of Kleinberg, to work incrementally with stream data. The proposed model is then used to extract sentimental bursts occurring within a specific mood label (for example, a burst of observing ‘shocked’). The blog posts at those time indices are analyzed to extract topics, and these are compared to real-world news events. Our comprehensive set of experiments conducted on a large-scale set of 12 million posts from Livejournal shows that the proposed sentiment index function coincides well with significant world events while bursts in sentiment allow us to locate finer-grain external world events.

Emotional reactions to real-world events in social networks

A convergence of emotions among people in social networks is potentially resulted by the occurrence of an unprecedented event in real world. E.g., a majority of bloggers would react angrily at the September 11 terrorist attacks. Based on this observation, we introduce a sentiment index, computed from the current mood tags in a collection of blog posts utilizing an affective lexicon, potentially revealing subtle events discussed in the blogosphere. We then develop a method for extracting events based on this index and its distribution. Our second contribution is establishment of a new bursty structure in text streams termed a sentiment burst. We employ a stochastic model to detect bursty periods of moods and the events associated. Our results on a dataset of more than 12 million mood-tagged blog posts over a 4-year period have shown that our sentiment-based bursty events are indeed meaningful, in several ways.

Leveraging Web 2.0 data for scalable semi-supervised learning of domain-specific sentiment lexicons

Since manually constructing domain-specific sentiment lexicons is extremely time consuming and it may not even be feasible for domains where linguistic expertise is not available. Research on the automatic construction of domain-specific sentiment lexicons has become a hot topic in recent years. The main contribution of this paper is the illustration of a novel semi-supervised learning method which exploits both term-to-term and document-to-term relations hidden in a corpus for the construction of domain specific sentiment lexicons. More specifically, the proposed two-pass pseudo labeling method combines shallow linguistic parsing and corpusbase statistical learning to make domain-specific sentiment extraction scalable with respect to the sheer volume of opinionated documents archived on the Internet these days. Another novelty of the proposed method is that it can utilize the readily available user-contributed labels of opinionated documents (e.g., the user ratings of product reviews) to bootstrap the performance of sentiment lexicon construction. Our experiments show that the proposed method can generate high quality domain-specific sentiment lexicons as directly assessed by human experts. Moreover, the system generated domain-specific sentiment lexicons can improve polarity prediction tasks at the document level by 2:18% when compared to other well-known baseline methods. Our research opens the door to the development of practical and scalable methods for domain-specific sentiment analysis.

Influence of medium range transport of particles from nucleation burst on particle number concentration within the urban airshed

An elevated particle number concentration (PNC) observed during nucleation events could play a significant contribution to the total particle load and therefore to the air pollution in the urban environments. Therefore, a field measurement study of PNC was commenced to investigate the temporal and spatial variations of PNC within the urban airshed of Brisbane, Australia. PNC was monitored at urban (QUT), roadside (WOO) and semi-urban (ROC) areas around the Brisbane region during 2009. During the morning traffic peak period, the highest relative fraction of PNC reached about 5% at QUT and WOO on weekdays. PNC peaks were observed around noon, which correlated with the highest solar radiation levels at all three stations, thus suggesting that high PNC levels were likely to be associated with new particle formation caused by photochemical reactions. Wind rose plots showed relatively higher PNC for the NE direction, which was associated with industrial pollution, accounting for 12%, 9% and 14% of overall PNC at QUT, WOO and ROC, respectively. Although there was no significant correlation between PNC at each station, the variation of PNC was well correlated among three stations during regional nucleation events. In addition, PNC at ROC was significantly influenced by upwind urban pollution during the nucleation burst events, with the average enrichment factor of 15.4. This study provides an insight into the influence of regional nucleation events on PNC in the Brisbane region and it the first study to quantify the effect of urban pollution on semi-urban PNC through the nucleation events. © 2012 Author(s).

Learning domain-specific sentiment lexicons for predicting product sales

Generic sentiment lexicons have been widely used for sentiment analysis these days. However, manually constructing sentiment lexicons is very time-consuming and it may not be feasible for certain application domains where annotation expertise is not available. One contribution of this paper is the development of a statistical learning based computational method for the automatic construction of domain-specific sentiment lexicons to enhance cross-domain sentiment analysis. Our initial experiments show that the proposed methodology can automatically generate domain-specific sentiment lexicons which contribute to improve the effectiveness of opinion retrieval at the document level. Another contribution of our work is that we show the feasibility of applying the sentiment metric derived based on the automatically constructed sentiment lexicons to predict product sales of certain product categories. Our research contributes to the development of more effective sentiment analysis system to extract business intelligence from numerous opinionated expressions posted to the Web

Changes in neutrophil surface receptor expression, degranulation, and respiratory burst activity after moderate- and high-intensity exercise

Intense exercise stimulates the systemic release of a variety of factors that alter neutrophil surface receptor expression and functional activity. These alterations may influence resistance to infection after intense exercise. The aim of this study was to examine the influence of exercise intensity on neutrophil receptor expression, degranulation (measured by plasma and intracellular myeloperoxidase concentrations), and respiratory burst activity. Ten well-trained male runners ran on a treadmill for 60 min at 60% [moderate-intensity exercise (MI)] and 85% maximal oxygen consumption [high-intensity exercise (HI)]. Blood was drawn immediately before and after exercise and at 1 h postexercise. Immediately after HI, the expression of the neutrophil receptor CD16 was significantly below preexercise values (P < 0.01), whereas MI significantly reduced CD35 expression below preexercise values (P < 0.05). One hour after exercise at both intensities, there was a significant decline in CD11b expression (P < 0.05) and a further decrease in CD16 expression compared with preexercise values (P < 0.01). CD16 expression was lower 1 h after HI than 1 h after MI (P < 0.01). Immediately after HI, intracellular myeloperoxidase concentration was less than preexercise values (P < 0.01), whereas plasma myeloperoxidase concentration was greater (P < 0.01), indicating that HI stimulated neutrophil degranulation. Plasma myeloperoxidase concentration was higher immediately after HI than after MI (P < 0.01). Neutrophil respiratory burst activity increased after HI (P < 0.01). In summary, both MI and HI reduced neutrophil surface receptor expression. Although CD16 expression was reduced to a greater extent after HI, this reduction did not impair neutrophil degranulation and respiratory burst activity.

Exercise-induced alterations in neutrophil degranulation and respiratory burst activity : possible mechanisms of action

Neutrophils constitute 50-60% of all circulating leukocytes; they present the first line of microbicidal defense and are involved in inflammatory responses. To examine immunocompetence in athletes, numerous studies have investigated the effects of exercise on the number of circulating neutrophils and their response to stimulation by chemotactic stimuli and activating factors. Exercise causes a biphasic increase in the number of neutrophils in the blood, arising from increases in catecholamine and cortisol concentrations. Moderate intensity exercise may enhance neutrophil respiratory burst activity, possibly through increases in the concentrations of growth hormone and the inflammatory cytokine IL-6. In contrast, intense or long duration exercise may suppress neutrophil degranulation and the production of reactive oxidants via elevated circulating concentrations of epinephrine (adrenaline) and cortisol. There is evidence of neutrophil degranulation and activation of the respiratory burst following exercise-induced muscle damage. In principle, improved responsiveness of neutrophils to stimulation following exercise of moderate intensity could mean that individuals participating in moderate exercise may have improved resistance to infection. Conversely, competitive athletes undertaking regular intense exercise may be at greater risk of contracting illness. However, there are limited data to support this concept. To elucidate the cellular mechanisms involved in the neutrophil responses to exercise, researchers have examined changes in the expression of cell membrane receptors, the production and release of reactive oxidants and more recently, calcium signaling. The investigation of possible modifications of other signal transduction events following exercise has not been possible because of current methodological limitations. At present, variation in exercise-induced alterations in neutrophil function appears to be due to differences in exercise protocols, training status, sampling points and laboratory assay techniques.

Online environmental citizenship : blogs, green marketing and consumer sentiment in the 21st Century

Over the last three decades, the rise in consumer generated content has enabled more environmentally conscious points of view to effect mainstream opinion (Kalafatis, Pollard, East & Tsogas, 1999; Barber, Taylor & Strick, 2009). Consequently, more people are buying into environmentalist ideology and organizing themselves to influence social change. Focus has shifted from attracting public awareness to concern for green ideas, discourse, and environmental citizenship, the latter becoming the guideline by which debates on such topics are regulated (Follows & Jobber, 2000; Dobson, 2003).

Neutrophil oxidative burst is primed by supernatant from stored red cells : implications for Transfusion-Related Acute Lung Injury (TRALI)

Aim/Background: Transfusion-related acute lung injury (TRALI) is a potentially fatal adverse transfusion reaction. It is hypothesised to occur via a two-insult mechanism: the recipient’s underlying co-morbidity in addition to the transfusion of blood products activate neutrophils in the lung resulting in damaged endothelium and capillary leakage. Neutrophil activation may occur by antibody or non-antibody related mechanisms, with the length of storage of cellular blood products implicated in the latter. This study investigated non-antibody mediated priming and/or activation of neutrophil oxidative burst. Methods: A cytochrome C reduction assay was used to assess priming and activation of neutrophil oxidative burst by pooled supernatant (SN) from day 1 (D1; n=75) and day 42 (D42; n=113) packed red blood cells (PRBC). Pooled PRBC-SN were assessed in parallel with PAF (priming), fMLP (activating), PAF + fMLP (priming + activating) and buffer only (negative) controls. Cytochrome C reduction was measured over 30min at 37oC (inclusive of 10min priming). Neutrophil activation by PRBC-SN was assessed cf. buffer only and neutrophil priming by PRBC-SN was assessed by co-incubation with fMLP cf. fMLP alone. One-way ANOVA; Newman-Keuls post-test; p<0.05; n=10 independent assays. Results: Neither D1- nor D42- PRBC-SN alone activated neutrophil oxidative burst. In addition, D1-PRBC-SN did not prime fMLP-activated neutrophil oxidative burst. D42-PRBC-SN did, however, prime neutrophils for subsequent activation of oxidative burst by fMLP, the magnitude of response being similar to PAF (a known neutrophil priming agonist). Conclusion: These findings are consistent with the two-insult mechanism of TRALI. Factors released into the SN during PRBC storage contributed to neutrophil priming synergistically with other neutrophil stimulating agonists. This implicates PRBC storage duration as a key factor contributing to non-immune neutrophil activation in the development of TRALI in patients with pre-disposing inflammatory conditions.

Integration of sentiment analysis into customer relational model : the importance of feature ontology and synonym

Online business or Electronic Commerce (EC) is getting popular among customers today, as a result large number of product reviews have been posted online by the customers. This information is very valuable not only for prospective customers to make decision on buying product but also for companies to gather information of customers’ satisfaction about their products. Opinion mining is used to capture customer reviews and separated this review into subjective expressions (sentiment word) and objective expressions (no sentiment word). This paper proposes a novel, multi-dimensional model for opinion mining, which integrates customers’ characteristics and their opinion about any products. The model captures subjective expression from product reviews and transfers to fact table before representing in multi-dimensions named as customers, products, time and location. Data warehouse techniques such as OLAP and Data Cubes were used to analyze opinionated sentences. A comprehensive way to calculate customers’ orientation on products’ features and attributes are presented in this paper.

Predicting stock market returns and volatility with investor sentiment : evidence from eight developed countries

We test the predictive ability of investor sentiment on the return and volatility at the aggregate market level in the U.S., four largest European countries and three Asia-Pacific countries. We find that in the U.S., France and Italy periods of high consumer confidence levels are followed by low market returns. In Japan both the level and the change in consumer confidence boost the market return in the next month. Further, shifts in sentiment significantly move conditional volatility in most of the countries, and in Italy such impacts lead to an increase in returns by 4.7% in the next month.

Investor sentiment as conditioning information in asset pricing

This paper assesses whether incorporating investor sentiment as conditioning information in asset-pricing models helps capture the impacts of the size, value, liquidity and momentum effects on risk-adjusted returns of individual stocks. We use survey sentiment measures and a composite index as proxies for investor sentiment. In our conditional framework, the size effect becomes less important in the conditional CAPM and is no longer significant in all the other models examined. Furthermore, the conditional models often capture the value, liquidity and momentum effects.

Initial design and physical characterization of a polymeric device for osmosis-driven delayed burst delivery of vaccines

Achieving the combination of delayed and immediate release of a vaccine from a delivery device without applying external triggers remains elusive in implementing single administration vaccination strategies. Here a means of vaccine delivery is presented, which exploits osmosis to trigger delayed burst release of an active compound. Poly(-caprolactone) capsules of 2 mm diameter were prepared by dip-coating, and their burst pressure and release characteristics were evaluated. Burst pressures (in bar) increased with wall thickness (t in mm) following Pburst = 131.t + 3.4 (R2 = 0.93). Upon immersion in PBS, glucose solution-filled capsules burst after 8.7 ± 2.9 days. Copolymers of hydrophobic  -caprolactone and hydrophilic polyethylene glycol were synthesized and their physico-chemical properties were assessed. With increasing hydrophilic content, the copolymer capsules showed increased water uptake rates and maximum weight increase, while the burst release was earlier: 5.6 ± 2.0 days and 1.9 ± 0.2 days for 5 and 10 wt% polyethylene glycol, respectively. The presented approach enables the reproducible preparation of capsules with high versatility in materials and properties, while these vaccine delivery vehicles can be prepared separately from, and independently of the active compound.

Synthesis and luminescent properties of star-burst D-Pi-A compounds based on 1,3,5-triazine core and carbazole end-capped phenylene ethynylene arms

Two new star-burst compounds based on 1,3,5-triazine core and carbazole end-capped phenylene ethynylene arms (1a and 1b) were synthesized and characterized. Their photophysical properties were investigated systematically via spectroscopic and theoretical methods. Both compounds exhibit strong 1π–π⁎ transitions in the UV region and intense 1π–π⁎/intramolecular charge transfer (1ICT) absorption bands in the UV–vis region. Introducing the carbazole end-capped phenylene ethynylene arm on the 1,3,5-triazine core causes a slight bathochromic shift and enhanced molar extinction coefficient of the 1π–π⁎/1ICT transition band. Both compounds are emissive in solution at room temperature and 77 K, which exhibit pronounced positive solvatochromic effect. The emitting state could be ascribed to 1ICT state in more polar solvent, and 1π–π⁎ state in low-polarity solvent. The high emission quantum yields (Φem=0.90~1.0) of 1a and 1b (in hexane and toluene) make them potential candidates as efficient light-emitting materials. The spectroscopic studies and theoretical calculations indicate that the photophysical properties of these compounds can be tuned by the carbazole end-capped phenylene ethynylene arm, which would also be useful for rational design of photofunctional materials.