Sentiment Analysis is a branch of Affective Computing usually considered a binary classification task. In this line of reasoning, Sentiment Analysis can be applied in several contexts to classify the attitude expressed in text samples, for example, movie reviews, sarcasm, among others. A common approach to represent text samples is the use of the Vector Space Model to compute numerical feature vectors consisting of the weight of terms. The most popular term weighting scheme is TF-IDF (Term Frequency - Inverse Document Frequency). It is an Unsupervised Weighting Scheme (UWS) since it does not consider the class information in the weighting of terms. Apart from that, there are Supervised Weighting Schemes (SWS), which consider the class information on term weighting calculation. Several SWS have been recently proposed, demonstrating better results than TF-IDF. In this scenario, this work presents a comparative study on different term weighting schemes and proposes a novel supervised term weighting scheme, named as TF-IDFC-RF (Term Frequency - Inverse Document Frequency in Class - Relevance Frequency). The effectiveness of TF-IDFC-RF is validated with SVM (Support Vector Machine) and NB (Naive Bayes) classifiers on four commonly used Sentiment Analysis datasets. TF-IDFC-RF outperforms all other weighting schemes and achieves F1 results of more than 99.9% on all datasets with SVM classifier.

Computers and robots are now learning to make decisions! Of course, "deciding" is a big word for machines that have no consciousness and whose level of "reasoning" is not even as evolved as that of a frog. But the latest developments in artificial intelligence (AI) are enough to frighten some and to arouse the fantasies of others. Between myth and reality, where exactly does the current research stand in this technology that threatens to disrupt all others? In its Wide Angle section, the Courier attempts to untangle the various paths of inquiry and offers some terminological signposts to help uninitiated readers to find their way through the fascinating but scary world of AI.

A crime is a punishable offence that is harmful for an individual and his society. It is obvious to comprehend the patterns of criminal activity to prevent them. Research can help society to prevent and solve crime activates. Study shows that only 10 percent offenders commits 50 percent of the total offences. The enforcement team can respond faster if they have early information and pre-knowledge about crime activities of the different points of a city. In this paper, supervised learning technique is used to predict crimes with better accuracy. The proposed system predicts crimes by analyzing data-set that contains records of previously committed crimes and their patterns. The system stands on two main algorithms - i) decision tree, and ii) k-nearest neighbor. Random Forest algorithm and Adaboost are used to increase the accuracy of the prediction. Finally, oversampling is used for better accuracy. The proposed system is feed with a criminal-activity data set of twelve years of San Francisco city.

We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime. We formulate the problem of generating curious behavior as one of meta-learning: an outer loop will search over a space of curiosity mechanisms that dynamically adapt the agent's reward signal, and an inner loop will perform standard reinforcement learning using the adapted reward signal. However, current meta-RL methods based on transferring neural network weights have only generalized between very similar tasks. To broaden the generalization, we instead propose to meta-learn algorithms: pieces of code similar to those designed by humans in ML papers. Our rich language of programs combines neural networks with other building blocks such as buffers, nearest-neighbor modules and custom loss functions. We demonstrate the effectiveness of the approach empirically, finding two novel curiosity algorithms that perform on par or better than human-designed published curiosity algorithms in domains as disparate as grid navigation with image inputs, acrobot, lunar lander, ant and hopper.

Through collecting a massively large number of tweets and building machine learning models, we investigate the dynamics of the Twitter social network formed by the interactions among millions of Twitter supporters. Our predictions are updated daily at 2AM.

The US is a leader in investing capital into private AI with nearly US$12 billion. China, which came second with US$6.8 billion investment, also files more AI patents than any other country across the globe and three times more than Japan. The majority of AI patents filed between 2014-2018 were filed in the U.S. and Canada, and 94% of patents are filed in wealthy nations. Mergers and acquisitions worth $37 billion were spurred thanks to AI. At the same time, IPOs worth $34 billion were also associated with AI. Investment in AI startups recorded a rapid increase in the last ten years from a total of $1.3 billion raised in 2010 to over $40.4 billion.

Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an adversarial text can only be created from a real-world text by replacing a few words. In many applications, these texts are limited in numbers, therefore their corresponding adversarial examples are often not diverse enough and sometimes hard to read, thus can be easily detected by humans and cannot create chaos at a large scale. In this paper, we propose an end to end solution to efficiently generate adversarial texts from scratch using generative models, which are not restricted to perturbing the given texts. We call it unrestricted adversarial text generation. Specifically, we train a conditional variational autoencoder (VAE) with an additional adversarial loss to guide the generation of adversarial examples. Moreover, to improve the validity of adversarial texts, we utilize discrimators and the training framework of generative adversarial networks (GANs) to make adversarial texts consistent with real data. Experimental results on sentiment analysis demonstrate the scalability and efficiency of our method. It can attack text classification models with a higher success rate than existing methods, and provide acceptable quality for humans in the meantime.

This stock market forecast evaluation report published recently by I Know First presents the performance of the stock market predictions generated by the I Know First AI Algorithm for Brazilian stock market, which showed significant results during 2019 and is expected to further grow by some 15% in 2020. The evaluation used two models - the Global Model which was sent only to institutional investors and the Daily Forecast Model which was daily delivered to both individual and institutional investors. The I Know First AI Algorithm picks top stocks to buy from Brazilian market by terms of their signal and predictability providing the user with the best Brazilian stocks set. The algorithm provides a selection of stocks identified as the most promising market opportunities and also indicates the reliability of asset-specific predictions. Global Model is a recently developed stock-picking method providing an alternative approach to investment selection process using more sophisticated filtering, in comparison to the company's Daily Forecast Model.

Artificial intelligence (AI) has the potential to solve many routine business challenges -- from quickly spotting a few questionable charges in thousands of invoices to predicting consumers' needs and wants. But there may be a flipside to these advances. Privacy concerns are cropping up as companies feed more and more consumer and vendor data into advanced, AI-fuelled algorithms to create new bits of sensitive information, unbeknownst to affected consumers and employees. This means that AI may create personal data. When it does, "it's data that has not been provided with [an individual's] consent or even with knowledge", said Chantal Bernier, assistant and interim privacy commissioner in the Office of the Privacy Commissioner of Canada from 2008 until 2014 who now consults in the privacy and cybersecurity practice of global law firm Dentons.

Artificial intelligence (AI) has the potential to solve many routine business challenges -- from quickly spotting a few questionable charges in thousands of invoices to predicting consumers' needs and wants. But there may be a flipside to these advances. Privacy concerns are cropping up as companies feed more and more consumer and vendor data into advanced, AI-fuelled algorithms to create new bits of sensitive information, unbeknownst to affected consumers and employees. This means that AI may create personal data. When it does, "it's data that has not been provided with [an individual's] consent or even with knowledge", said Chantal Bernier, assistant and interim privacy commissioner in the Office of the Privacy Commissioner of Canada from 2008 until 2014 who now consults in the privacy and cybersecurity practice of global law firm Dentons.