Scientific articles are not born equal. Some generate an entire discipline while others make relatively fewer contributions. When reviewing scientific literatures, it would be useful to identify those important articles and understand how they influence others. In this paper, we introduce J-Index, a quantitative metric modeling topic-level academic influence. J-Index is calculated based on the novelty of each article as well as its contributions to the articles where it is cited. We devise a generative model named Reference Topic Model (RefTM) which jointly utilizes the textual content and citation information in scientific literatures. We show how to learn RefTM to discover both the novelty of each paper and the strength of each citation. Experiments on a collection of more than 420,000 research papers demonstrate that RefTM outperforms the state-of-the-art approaches in terms of topic coherence as well as prediction performance, and validate J-Index's effectiveness of capturing topic-level academic influence in scientific literatures.

In this paper, we propose an intelligent dialogue agent for the IoT home. The goal of the proposed system is to efficiently control IoT devices with natural spoken dialogue. This system is made up of the following components: Spoken Language Understanding for analyzing textual input and understanding user intention, Dialogue Management with a State Manager that consists of dialogue policies, Context Manager for understanding the environment, Action Planner responsible for generating a sequence of actions to achieve user intention, Things Manager for observing and controlling IoT devices, and Natural Language Generation that generates natural language from computer-based representation. This system is fully implemented in software and is evaluated in a real IoT home environment.

Synopsis: There is more to Text Mining than TDM and TF-IDF. Come explore the world of Sentiment Analysis using Advanced Text Mining techniques with cutting edge tools like Stanford's CoreNLP and analysing it's output using Python. Speaker: Aditya Shankar is a Lecturer in the Intelligent Systems practice at the Institute of Systems Science in the National University of Singapore. He started his career consulting for Microsoft in Redmond, WA, Nike in Portland, OR and T-Mobile in Seattle, WA. He then moved on to work for companies in the Healthcare domain, mostly healthcare providers in Tennessee.

Topic models (e.g., pLSA, LDA, SLDA) have been widely used for segmenting imagery. These models are confined to crisp segmentation. Yet, there are many images in which some regions cannot be assigned a crisp label (e.g., transition regions between a foggy sky and the ground or between sand and water at a beach). In these cases, a visual word is best represented with partial memberships across multiple topics. To address this, we present a partial membership latent Dirichlet allocation (PM-LDA) model and associated parameter estimation algorithms. Experimental results on two natural image datasets and one SONAR image dataset show that PM-LDA can produce both crisp and soft semantic image segmentations; a capability existing methods do not have.

I have been trying to use ML for sentiment analysis of sentences, I have been successful with Naive Bayes and SVM but I would like to implement Neural Networks for Sentiment Analysis but couldn't find a way to convert words as input for neural networks. I know that representing word as a numerical is not efficient. How is nlpnet implemented, I tried to understand that but that flew over my head.

Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. This model enables us to naturally exploit the semantic structures of word embeddings while flexibly discovering the number of topics. Experiments demonstrate that our method outperforms competitive approaches in terms of topic coherence on two different text corpora while offering efficient inference.

Identify the top four metrics that drive sales among the metrics that I have suggested in this article (by all means, please do not ignore external data sources - including a sentiment analysis index by product, that is, what your customers write about your products on Twitter), and create a simple regression model. You could get it done with Excel (use the data analysis plug-in or the linest functions) and get better forecasts than using a much more sophisticated model based only on internal data coming from just one of your many silos. Get confidence intervals for your sales forecasts: more about this in a few days; I will provide a very simple, model-free, data-driven solution to compute confidence intervals.

In this article we will show how you can build a simple Sentiment Analysis tool which classifies tweets as positive, negative or neutral by using the Twitter REST API 1.1v and the Datumbox API 1.0v.

Sentiment Analysis (detecting document's polarity, subjectivity and emotional states) is a difficult problem and several times I bumped into unexpected and interesting results. One of the strangest things that I found is that despite the fact that neutral class can improve under specific conditions the classification accuracy, it is often ignored by most researchers.

As it turns out, other techniques including website path analysis, text analysis of customer feedback, sentiment analysis of social media, and graph analysis --all distinctly different analytics techniques with each delivering insights complementing the others--revealed a fuller picture: people weren't complaining about price, preferring the cheaper item, or any of the things that the retailer expected. Instead, customers were complaining about how hard it was to find designer jeans on the website. It was a website navigation issue. And the issue was invisible until the retailer made sense of analytics from a variety of sources.