Automated sentiment classification (SC) on short text fragments has received increasing attention in recent years. Performing SC on unseen domains with few or no labeled samples can significantly affect the classification performance due to different expression of sentiment in source and target domain. In this study, we aim to mitigate this undesired impact by proposing a methodology based on a predictive measure, which allows us to select an optimal source domain from a set of candidates. The proposed measure is a linear combination of well-known distance functions between probability distributions supported on the source and target domains (e.g. Earth Mover's distance and Kullback-Leibler divergence). The performance of the proposed methodology is validated through an SC case study in which our numerical experiments suggest a significant improvement in the cross domain classification error in comparison with a random selected source domain for both a naive and adaptive learning setting. In the case of more heterogeneous datasets, the predictability feature of the proposed model can be utilized to further select a subset of candidate domains, where the corresponding classifier outperforms the one trained on all available source domains. This observation reinforces a hypothesis that our proposed model may also be deployed as a means to filter out redundant information during a training phase of SC.

A number of techniques have been proposed for aspect discovery using part of speech tagging (Hu and Liu, 2004), syntactic parsing (Lu et al., 2009), clustering (Mei et al., 2007; Titov and McDonald, 2008b), data mining (Ku et al., 2006), and information extraction (Popescu and Etzioni, 2005). Various lexicon and rule-based methods (Hu and Liu, 2004; Ku et al., 2006; Blair-Goldensohn et al., 2008) have been adopted for sentiment prediction together with a few learning approaches (Lu et al., 2009; Pappas and Popescu-Belis, 2017; Angelidis and Lapata, 2018). As for the summaries, a common format involves a list of aspects and the number of positive and negative opinions for each (Hu and Liu, 2004). While this format gives an overall idea of people's opinion, reading the actual text might be necessary to gain a better understanding of specific details. Textual summaries are created following mostly extractive methods (but see Ganesan et al. 2010 for an abstractive approach), and various formats ranging from lists of words (Popescu and Etzioni, 2005), to phrases (Lu et al., 2009), and sentences (Mei et al., 2007; Blair-Goldensohn et al., 2008; Lerman et al., 2009; Wang and Ling, 2016). In this paper, we present a neural framework for opinion extraction from product reviews. We follow the standard architecture for aspect-based summarization, while taking advantage of the success of neural network models in learning continuous features without recourse to preprocessing tools or linguistic annotations.

Sentiment analysis is perhaps one of the most popular applications of NLP, with a vast number of tutorials, courses, and applications that focus on analyzing sentiments of diverse datasets ranging from corporate surveys to movie reviews. The key aspect of sentiment analysis is to analyze a body of text for understanding the opinion expressed by it. Typically, we quantify this sentiment with a positive or negative value, called polarity. The overall sentiment is often inferred as positive, neutral or negative from the sign of the polarity score. Usually, sentiment analysis works best on text that has a subjective context than on text with only an objective context.

Onavo, Facebook's data security app that offers consumers access to a virtual private network (VPN), is due to be removed from Apple's App Store at the same time that the social media site suspended more than 400 apps for harvesting users' personal information. As reported by The Wall Street Journal, the app created an encrypted VPN connection that routes internet activity through servers that are managed and secured by Facebook and the app also alerted users when sites they visit may be dangerous. It has become public knowledge that Facebook is able to collate data about how people use their smartphones outside of the social network's services and potentially figure out information about rivals or internet trends, but what is Onavo? Onavo, founded in Israel in 2010 by Roi Tiger and Guy Rosen, is an analytics company that has provided products for applications, which are then influenced by the data that is collated through the company's VPN services, Onavo Extend and Onavo Protect, according to Crunchbase. In 2013, the company was acquired by Facebook and was the seed for the launch of Facebook Israel, its platform being leveraged to monitor the performance of competitors and influence other acquisitions and business decisions.

LinkedIn will open up its data to academic researchers for the purpose of better understanding the labor market and the economy, Bloomberg reports. The company is inviting academics to submit study proposals that in some way involve analytics, economics or artificial intelligence and it will select projects early next year. If chosen, researchers will then get access to "one of the largest and most robust datasets of professional and economic networks," according to LinkedIn Chief Data Officer Igor Perisic. In a post-Cambridge Analytica world, giving researchers access to troves of user data may not seem like the best plan. But LinkedIn has put a number of protections in place to ensure its users' privacy isn't violated.

Twitter has provided a great opportunity for public libraries to disseminate information for a variety of purposes. Twitter data have been applied in different domains such as health, politics, and history. There are thousands of public libraries in the US, but no study has yet investigated the content of their social media posts like tweets to find their interests. Moreover, traditional content analysis of Twitter content is not an efficient task for exploring thousands of tweets. Therefore, there is a need for automatic methods to overcome the limitations of manual methods. This paper proposes a computational approach to collecting and analyzing using Twitter Application Programming Interfaces (API) and investigates more than 138,000 tweets from 48 US west coast libraries using topic modeling. We found 20 topics and assigned them to five categories including public relations, book, event, training, and social good. Our results show that the US west coast libraries are more interested in using Twitter for public relations and book-related events. This research has both practical and theoretical applications for libraries as well as other organizations to explore social media actives of their customer and themselves.

Analytics company Crimson Hexagon says Facebook has reinstated its data access to Facebook and Instagram. That access was suspended last month, with Facebook saying it was investigating whether the company had violated any of its data use policies. In this case, the issue appears to be related to some of Crimson Hexagon's contracts with the U.S. government, with Facebook saying it wasn't aware of those contracts when contacted by The Wall Street Journal. What followed, according to a blog post by Crimson Hexagon Dan Shore, was "several weeks of constructive discussion and information exchange." It seems that Facebook was satisfied with what it learned and ended Crimson Hexagon's suspension. Shore said that government customers make up less than 5 percent of the company's business, adding, "To our knowledge, no government customer has used the Crimson Hexagon platform for surveillance of any individual or group."

This week, I'm writing a series of articles about sentiment analysis, which is often referred to as Emotional AI. Engineers of this new brand of technology claim to be able to detect and analyze emotion using electronic sensors and machine learning. To date, media coverage of this emerging field of has been rather credulous, accepting Silicon Valley's assertions about Emotional AI at face value. In this series, I'm attempting to balance that fawning coverage with critical questions, building toward suggestions for ways in which sentiment analysis can be more meaningfully employed by businesses that sincerely wish to enhance their emotional connection with the human beings they serve. This is the fourth article in the series, which also includes the following: Can AI Understand Your Emotions?

Lifelong Machine Learning, Second Edition is an introduction to an advanced machine learning paradigm that continuously learns by accumulating past knowledge that it then uses in future learning and problem solving. In contrast, the current dominant machine learning paradigm learns in isolation: given a training dataset, it runs a machine learning algorithm on the dataset to produce a model that is then used in its intended application. It makes no attempt to retain the learned knowledge and use it in subsequent learning. Unlike this isolated system, humans learn effectively with only a few examples precisely because our learning is very knowledge-driven: the knowledge learned in the past helps us learn new things with little data or effort. Lifelong learning aims to emulate this capability, because without it, an AI system cannot be considered truly intelligent.

Table 1: Text Mining and Text Analytics Linguistic and statistical approaches for processing text provide complementary results for extracting value from unstructured textual data. Though each has been practiced independently, the most effective solutions combine their strengths. This balances the precision of linguistically based text analytics with the powerful recall of a statistical text mining approach. The rapid growth of "big data" and predictive analytics means that the best techniques for achieving this balance will be constantly evolving, yet the tools exist today to make great progress on the wide variety of textual analytics challenges.