We propose a new approach to opinion mining that relies not on explicit occurrences of opinions in economic texts but on implicit ones extracted from the polarity of the discussed economic subtopic. ...We prove that the majority of economic texts contain personal opinions that can be retrieved based solely on the implicit opinions within. We rely on cooccurrences of economic indicators and future state modifiers to determine the polarity of each text. We benchmark the method's results with those obtained using SentiWordNet. Key words: opinion mining, economics, SentiWordNet
Despite significant progress toward super resolving more realistic images by deeper convolutional neural networks (CNNs), reconstructing fine and natural textures still remains a challenging problem. ...Recent works on single image super resolution (SISR) are mostly based on optimizing pixel and content wise similarity between recovered and high-resolution (HR) images and do not benefit from recognizability of semantic classes. In this paper, we introduce a novel approach using categorical information to tackle the SISR problem; we present an encoder architecture able to extract and use semantic information to super-resolve a given image by using multitask learning, simultaneously for image super-resolution and semantic segmentation. To explore categorical information during training, the proposed decoder only employs one shared deep network for two task-specific output layers. At run-time only layers resulting HR image are used and no segmentation label is required. Extensive perceptual experiments and a user study on images randomly selected from COCO-Stuff dataset demonstrate the effectiveness of our proposed method and it outperforms the state-of-the-art methods.
Emoticons are widely used to express positive or negative sentiment on Twitter. We report on a study with live users to determine whether emoticons are used to merely emphasize the sentiment of ...tweets, or whether they are the main elements carrying the sentiment. We found that the sentiment of an emoticon is in substantial agreement with the sentiment of the entire tweet. Thus, emoticons are useful as predictors of tweet sentiment and should not be ignored in sentiment classification. However, the sentiment expressed by an emoticon agrees with the sentiment of the accompanying text only slightly better than random. Thus, using the text accompanying emoticons to train sentiment models is not likely to produce the best results, a fact that we show by comparing lexicons generated using emoticons with others generated using simple textual features.
Super-resolution (SR) has traditionally been based on pairs of high-resolution images (HR) and their low-resolution (LR) counterparts obtained artificially with bicubic downsampling. However, in ...real-world SR, there is a large variety of realistic image degradations and analytically modeling these realistic degradations can prove quite difficult. In this work, we propose to handle real-world SR by splitting this ill-posed problem into two comparatively more well-posed steps. First, we train a network to transform real LR images to the space of bicubically down-sampled images in a supervised manner, by using both real LR/HR pairs and synthetic pairs. Second, we take a generic SR network trained on bicubically downsampled images to super-resolve the transformed LR image. The first step of the pipeline addresses the problem by registering the large variety of degraded images to a common, well understood space of images. The second step then leverages the already impressive performance of SR on bicubically downsampled images, sidestepping the issues of end-to-end training on datasets with many different image degradations. We demonstrate the effectiveness of our proposed method by comparing it to recent methods in real-world SR and show that our proposed approach outperforms the state-of-the-art works in terms of both qualitative and quantitative results, as well as results of an extensive user study conducted on several real image datasets.
Many Artificial Intelligence tasks need large amounts of commonsense knowledge. Because obtaining this knowledge through machine learning would require a huge amount of data, a better alternative is ...to elicit it from people through human computation. We consider the sentiment classification task, where knowledge about the contexts that impact word polarities is crucial, but hard to acquire from data. We describe a novel task design that allows us to crowdsource this knowledge through Amazon Mechanical Turk with high quality. We show that the commonsense knowledge acquired in this way dramatically improves the performance of established sentiment classification methods.
We investigated the influence of valence shifters on sentiment analysis within a new model built to extract opinions from economic texts. The system relies on implicit convictions that emerge from ...the studied texts through co-occurrences of economic indicators and future state modifiers. The polarity of the modifiers can however easily be reversed using negations, diminishers or intensifiers. We compared the system results with and without counting the effect of negations and future state modifier strength and we found that results better than chance are rarely achieved in the second case. In the first case however we proved that the opinion polarity identification accuracy is similar or better than that of other similar tests. Furthermore we found that, when applied to economic indicators, diminishers have the effect of negations.