One of the major hurdles preventing the full exploitation of information from online communities is the widespread concern regarding the quality and credibility of user-contributed content. Prior works in this domain operate on a static snapshot of the community, making strong assumptions about the structure of the data (e.g., relational tables), or consider only shallow features for text classification. To address the above limitations, we propose probabilistic graphical models that can leverage the joint interplay between multiple factors in online communities --- like user interactions, community dynamics, and textual content --- to automatically assess the credibility of user-contributed online content, and the expertise of users and their evolution with user-interpretable explanation. To this end, we devise new models based on Conditional Random Fields for different settings like incorporating partial expert knowledge for semi-supervised learning, and handling discrete labels as well as numeric ratings for fine-grained analysis. This enables applications such as extracting reliable side-effects of drugs from user-contributed posts in healthforums, and identifying credible content in news communities. Online communities are dynamic, as users join and leave, adapt to evolving trends, and mature over time. To capture this dynamics, we propose generative models based on Hidden Markov Model, Latent Dirichlet Allocation, and Brownian Motion to trace the continuous evolution of user expertise and their language model over time. This allows us to identify expert users and credible content jointly over time, improving state-of-the-art recommender systems by explicitly considering the maturity of users. This also enables applications such as identifying helpful product reviews, and detecting fake and anomalous reviews with limited information.

When experimenting with machine learning and big data, you may identify data sets that contain streams of text that contain customer reviews, or social media posts where customers (or potential customers) are talking about a product, brand or service that you offer. Mining such data to determine how people feel about your product, brand, or service, is called Sentiment Analysis. People have always had an interest in what people think, or what their opinion is. Since the inception of the internet, increasing numbers of people are using websites and services to express their opinion. With social media channels such as Facebook, LinkedIn, and Twitter, it is becoming feasible to automate and gauge what public opinion is on a given topic, news story, product, or brand.

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly balances two goals: recovery of faithful generative explanations of high-dimensional data, and accurate prediction of associated semantic labels. Existing approaches fail to achieve these goals due to an incomplete treatment of a fundamental asymmetry: the intended application is always predicting labels from data, not data from labels. Our prediction-constrained objective for training generative models coherently integrates loss-based supervisory signals while enabling effective semi-supervised learning from partially labeled data. We derive learning algorithms for semi-supervised mixture and topic models using stochastic gradient descent with automatic differentiation. We demonstrate improved prediction quality compared to several previous supervised topic models, achieving predictions competitive with high-dimensional logistic regression on text sentiment analysis and electronic health records tasks while simultaneously learning interpretable topics.

Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal reward component weighting. To render this search feasible, we use multi-objective reinforcement learning to significantly reduce the number of training dialogues required. We apply our proposed method to find optimized component weights for six domains and compare them to a default baseline.

For our case we only consider Text feature of the Tweet as we are interested on the review of the movie. We can also use the other features such as Latitude/Longitude, replied to, etc. do other analysis on the tweeted data.

Conference Topics Topics at this conference include, but are not limited to: Business Analytics - Methods: Dimensionality Reduction, Feature Extraction, and Feature Selection Supervised, Semi-Supervised, and Unsupervised Methods Statistical Learning Theory Online Learning, Data Stream Mining, and Dynamic Data Mining Graph Mining and Semi-Structured Data patial and Temporal Data Mining Deep Learning and Neural Network Research Large Scale Data Mining Uncertainty Modeling in Data Mining Business Analytics - Applications: Credit Scoring and Financial Modeling Forecasting Fraud Detection Web Intelligence and Information Retrieval Marketing, Business Intelligence, and e-Commerce Decision Analysis and Decision Support Systems Social Network Analysis Privacy-preserving Data Mining and Privacy-related Issue Text Mining, Sentiment Analysis, and Opinion Mining Important Dates July 31, 2017: Deadline for submission of extended abstracts August 15, 2017: Accept/reject decision November 15, 2017: Deadline for early registration January 17-19, 2018: BAFI 2018 *Only one contributed abstract is accepted from the same presenting author. Submission Guidelines Authors are requested to submit a 600 word abstract in English using the platform available at the EasyChair system. Please do not attach any additional files at this time.

Topic models have been extensively used to organize and interpret the contents of large, unstructured corpora of text documents. Although topic models often perform well on traditional training vs. test set evaluations, it is often the case that the results of a topic model do not align with human interpretation. This interpretability fallacy is largely due to the unsupervised nature of topic models, which prohibits any user guidance on the results of a model. In this paper, we introduce a semi-supervised method called topic supervised non-negative matrix factorization (TS-NMF) that enables the user to provide labeled example documents to promote the discovery of more meaningful semantic structure of a corpus. In this way, the results of TS-NMF better match the intuition and desired labeling of the user. The core of TS-NMF relies on solving a non-convex optimization problem for which we derive an iterative algorithm that is shown to be monotonic and convergent to a local optimum. We demonstrate the practical utility of TS-NMF on the Reuters and PubMed corpora, and find that TS-NMF is especially useful for conceptual or broad topics, where topic key terms are not well understood. Although identifying an optimal latent structure for the data is not a primary objective of the proposed approach, we find that TS-NMF achieves higher weighted Jaccard similarity scores than the contemporary methods, (unsupervised) NMF and latent Dirichlet allocation, at supervision rates as low as 10% to 20%.

Artificial Intelligence, Machine Learning and Sentiment Analysis are changing the way in which numerous client services are offered. In particular, Financial Organisations are creating and leveraging such innovation in the domain of wealth management. This trend is now being taken on board by multiple innovators: academia, start-ups, technology companies and financial market participants. AI and Machine Learning have emerged as a central aspect of analytics which is applied to multiple domains. AI and Machine Learning, Pattern classifiers and natural language processing (NLP) underpin Sentiment Analysis (SA); SA is a technology that makes rapid assessment of the sentiments expressed in news releases as well as other media sources such as Twitter and blogs.

Sentiment analysis is extremely useful us to gain an overview of the public opinion behind certain topics and feedbacks. Automatically classifying text by sentiment allows you to easily find out the general opinions of people in your area of interest. For example, you might want to analyze reviews of a product to help you improve the customer experience, or to find the most or least popular product. The Obama used sentiment analysis to gauge public opinion to policy announcements and campaign messages ahead of 2012 presidential election. How can we get this?

Learn how to build a sentiment analysis solution for social media analytics by bringing real-time Twitter events into Azure Event Hubs. In this scenario, you write an Azure Stream Analytics query to analyze the data. Then you either store the results for later use or use a dashboard and Power BI to provide insights in real time. Social media analytics tools help organizations understand trending topics. Trending topics are subjects and attitudes that have a high volume of posts in social media.