Visual sentiment analysis, which studies the emotional response of humans on visual stimuli such as images and videos, has been an interesting and challenging problem. It tries to understand the high-level content of visual data. The success of current models can be attributed to the development of robust algorithms from computer vision. Most of the existing models try to solve the problem by proposing either robust features or more complex models. In particular, visual features from the whole image or video are the main proposed inputs. Little attention has been paid to local areas, which we believe is pretty relevant to human's emotional response to the whole image. In this work, we study the impact of local image regions on visual sentiment analysis. Our proposed model utilizes the recent studied attention mechanism to jointly discover the relevant local regions and build a sentiment classifier on top of these local regions. The experimental results suggest that 1) our model is capable of automatically discovering sentimental local regions of given images and 2) it outperforms existing state-of-the-art algorithms to visual sentiment analysis.

If you attend a protest in Washington, D.C., nowadays, better plan on leaving your cellphone at home. That is, unless you want police to confiscate it, mine it for incriminating information and then gather even more data from their BFF -- Facebook. At least one person arrested during protests on Inauguration Day got an email from Facebook's Law Enforcement Response Team alerting them that investigators wanted access to their data. Another received a Facebook data subpoena. The email was basically a countdown to when Facebook inevitably handed that data over to D.C. police. That is, unless the respondent figured out how to file an objection within a 10-day window.

According to the World Bank, risky behaviors are increasingly widespread globally and pose a growing threat to individual health and society. Recently, a number of studies have been done to study risky behaviors, such as understanding illicit drug use behaviors using social media data, and predicting drinking behavior and alcohol-related problems among fraternity and sorority members. However, the majority of the related work only focuses on one risky behavior. Research in clinical psychology and public health domains tell us that there may exist some correlations among risk behaviors. In this paper, in order to support and utilize this correlation, we investigate five risky behaviors: drug consumption, drinking, sleep disorder, depression, and eating disorder. We utilize Instagram data to discover the correlation between those five risk behaviors and employ multi-task machine learning techniques to predict the potential risk behaviors in the near future for the Instagram users.

This blog post is the result of my efforts to show to a coworker how to get the insights he needed by using the streaming capabilities and concise API of Apache Spark. In this blog post, you'll learn how to do some simple, yet very interesting analytics that will help you solve real problems by analyzing specific areas of a social network. Using a subset of a Twitter stream was the perfect choice to use in this demonstration, since it had everything we needed: an endless and continuous data source that was ready to be explored. Spark Streaming is very well explained here and in chapter 6 of the ebook "Getting Started with Apache Spark," so we are going to skip some of the details about the Streaming API and move on to setting up our app. Let's see how to prepare our app before doing anything else.

Natural language processing technologies, which are the basis for sentiment analysis of social media platforms and are deployed in some search engine results, can recognize the intended meanings of terms despite different spellings, diction, connotations, and languages, making integration and analytics efforts more comprehensive. These cognitive computing capabilities are responsible for the parsing of unparalleled quantities of big data in integration and analytics efforts in the healthcare space, facilitating advancements in research and treatment options and testing optimization and enhancing master data management. These capabilities can also incorporate real-time geospatial, weather, news, and industry-specific data to influence marketing, sales, and investment opportunities in any number of verticals. Significantly, natural language processing can also provide explanations for analytics results and recommendations, effectively qualifying quantitative facts.

Open information extraction (open IE) refers to the extraction of structured relation triples from plain text, such that the schema for these relations does not need to be specified in advance. For example, Barack Obama was born in Hawaii would create a triple (Barack Obama; was born in; Hawaii), corresponding to the open domain relation "was born in". The system first splits each sentence into a set of entailed clauses. Each clause is then maximally shortened, producing a set of entailed shorter sentence fragments. These fragments are then segmented into OpenIE triples, and output by the system.

Already, as of 2010, a quarter of Americans (24 percent) had posted product reviews or comments online, and 78 percent of internet users had gone online for product research. But those are ancient stats. More recently, BrightLocal found in 2016 that 91 percent of consumers regularly or occasionally read online reviews, with 47 percent taking sentiment of local-business reviews -- the tonality of a review's text -- into account in purchasing decisions. Breaking out the figures, 74 percent of consumers say that positive reviews make them trust a local business more, and 60 percent say that negative reviews make them not want to use a business, according to BrightLocal. So reviews are important, and the feelings expressed are key.

What initially began as a Facebook event has morphed into a cultural moment, a juxtaposition of the previous day's inauguration of America's 45th president, Donald Trump. Heather Whaling is CEO of Geben Communication, a PR and social media agency with offices in Columbus, Ohio, and Chicago. She serves on the board of The Women's Fund of Central Ohio, mentors women entrepreneurs, and is a vocal advocate for paid parental leave. On the issues, it's increasingly difficult to find commonalities between Trump supporters and the marchers who will flock to DC and other cities around the country. Yet both groups share at least one tool in their toolbox: A mastery of social media as the go-to channel to amplify viewpoints and shape perceptions.

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank Semantic word spaces have been very useful but cannot express the meaning of longer phrases in a principled way. Further progress towards understanding compositionality in tasks such as sentiment detection requires richer supervised training and evaluation resources and more powerful models of composition. To remedy this, we introduce a Sentiment Treebank. It includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality. To address them, we introduce the Recursive Neural Tensor Network.

The Consortium for Lexical Research was operated by the Computing Research Laboratory at New Mexico State University, until December 1, 1995, when it ceased operation due to lack of funding support. The Consortium maintained a collection of lexical resources that were available to members. Now that the center no longer exists, CRL has made the files of CLR available free of charge to all interested parties. Although the resources are no longer maintained and updated, and hence can become out of date, they are still a very valuable source of information for information extraction system building.