1,721,459 research outputs found
Fine-Tuning of Word Embeddings for Semantic Sentiment Analysis
No full textIn this paper, we present a state-of-the-art deep-learning approach for sentiment polarity classification. Our approach is based on a 2-layer bidirectional Long Short-Term Memory network, equipped with a neural attention mechanism to detect the most informative words in a natural language text. We test different pre-trained word embeddings, initially keeping these features frozen during the first epochs of the training process. Next, we allow the neural network to perform a fine-tuning of the word embeddings for the sentiment polarity classification task. This allows projecting the pre-trained embeddings in a new space which takes into account information about the polarity of each word, thereby being more suitable for semantic sentiment analysis. Experimental results are promising and show that the fine-tuning of the embeddings with a neural attention mechanism allows boosting the performance of the classifier
Bearish-bullish sentiment analysis on financial microblogs
No full textUser-generated data in blogs and social networks has recently become a valuable resource for sentiment analysis in the financial domain since it has been shown to be extremely significant to marketing research companies and public opinion organizations. In this paper a fine-grained approach is proposed to predict a real-valued sentiment score. We use several feature sets consisting of lexical features, semantic features and combination of lexical and semantic features. To evaluate our approach a microblog messages dataset is used. Since our dataset includes confidence scores of real numbers within the [0-1] range, we compare the performance of two learning methods: Random Forest and SVR. We test the results of the training model boosted by semantics against classification results obtained by n-grams. Our results indicate that our approach succeeds in performing the accuracy level of more than 72% in some cases
Survey on Videos Data Augmentation for Deep Learning Models
No full textIn most Computer Vision applications, Deep Learning models achieve state-of-the-art performances. One drawback of Deep Learning is the large amount of data needed to train the models. Unfortunately, in many applications, data are difficult or expensive to collect. Data augmentation can alleviate the problem, generating new data from a smaller initial dataset. Geometric and color space image augmentation methods can increase accuracy of Deep Learning models but are often not enough. More advanced solutions are Domain Randomization methods or the use of simulation to artificially generate the missing data. Data augmentation algorithms are usually specifically designed for single images. Most recently, Deep Learning models have been applied to the analysis of video sequences. The aim of this paper is to perform an exhaustive study of the novel techniques of video data augmentation for Deep Learning models and to point out the future directions of the research on this topic
Proceedings of the 3rd International Workshop at ESWC on Emotions, Modality, Sentiment Analysis and the Semantic Web co-located with 14th ESWC 2017, Portroz, Slovenia, May 28, 2017
No full textA Peak-Shaving-Oriented Incentive Mechanism for Smart Grids
No full textProsumers play a crucial role in smart grids, especially within local energy communities (LECs), since they can both consume and produce energy. When peer-to-peer (P2P) energy trading is available, prosumers can exchange their produced energy with each other: if done properly, this may lead to better energy self-consumption throughout the grid, resulting in reduced transmission losses, lower energy costs, and decreased wear and tear to the grid. Previous work on this topic led to a mechanism capable of obtaining several such goals, like preventing intentional energy production curtailment, disincentivizing simultaneous energy consumption that may lead to congestions, encouraging users to consume their own produced energy as much as possible, and ensuring that even if users initially create schedules with a selfish approach, they will ultimately converge upon a configuration that garners mutual agreement. However, this mechanism has not yet been analyzed from the perspective of peak shaving. Therefore, this paper aims to cover this shortcoming. Our objective in this work is to create a new mechanism that, under certain conditions, guarantees the achievement of optimal peak shaving. We will use it as a baseline to compare the existing mechanisms and understand under which conditions it leads to peak shaving. We performed simulations on a dataset from a grid in Cardiff, UK, and the results show that the existing mechanisms achieve optimal peak shaving both if the users act selfishly, and if they are allowed to form coalitions among themselves
Toward a green internet
No full textMethods for energy efficiency savings will be needed to meet the growing demands of increasing Internet usag
Towards Seamless Human-Robot Dialogue through a Robot Action Ontology
No full textThis research paper introduces a novel methodology enabling the Zora humanoid robot to effectively engage in dynamic interactions by responding to user queries and complementing its responses with appropriate gestures. Notably, these inquiries may extend beyond mere questions to encompass action commands articulated by the user, which the robot proficiently recognizes and executes. The integration of a Large Language Model enhances the system's capabilities, particularly in the domain of questionanswering. To bolster the recognition and execution of action commands, we have employed a robot action ontology established in previous research endeavors. This ontology defines relevant classes and individuals, forming the basis for a nuanced understanding of user-inputted action commands. Further refinement involves the generation of succinct three-word strings for each action, ensuring semantic alignment with the user's verbal instructions. Importantly, our system operates in two distinctive modes: STATELESS and STATEFUL. In STATEFUL mode, the robot possesses awareness of its present posture, allowing it to execute action commands only when they align with its current state. This adaptive feature enhances the overall effectiveness of the system, catering to the dynamic nature of human-robot interactions and promoting a seamless and contextually aware dialogue between the NAO humanoid robot and its users
A new unsupervised method for Document Clustering by using WordNet Lexical and Conceptual Relations
No full text- …
