Integrating commonsense knowledge with GPT embeddings for emotion classification☆

CoMaSa:Context Multi-aware Self-attention for emotional response generation

We present an online multilingual system for event detection and comprehension from media feeds. The system retrieves information from news sites, aggregates them into events (event detection), and summarizes them by extracting semantic labels of its most relevant entities (event representation) in order to answer the journalism Ws: who, what, when and where. The generated events populate VLX-Stories -an event ontology- transforming unstructured text data to a structured knowledge base representation. Our system exploits an external entity Knowledge Graph (VKG) to help populate VLX-Stories. At the same time, this external knowledge graph can also be extended with a Dynamic Entity Linking (DEL) module, which detects emerging entities (EE) on unstructured data. The system is currently deployed in production and used by media producers in the editorial process, providing real-time access to breaking news. Each month, VLX-Stories detects over 9000 events from over 4000 news feeds from seven different countries and in three different languages. At the same time, it detects over 1300 EE per month, which populate VKG.

Recently, people used social media to convey their emotions in the text. Text classification is required for group a text containing emotion or not and identify the type of emotion. Most of the research in emotion classification use machine learning methods. So this research offers the use of deep learning for the classification of emotions in text. One of the algorithms that is widely used for deep learning is BERT (Bidirectional Encoder Representations from Transformers). For the experiment, classification is divided into two phases, namely the first phase groups emotion or not emotion tweets, and the second phase groups emotion tweets into five types of emotions, namely happy, angry, sad, scared and surprised. The experiment uses three data scenarios, namely the commuter line, transjakarta and combination data. The BERT method was compared with the BiLSTM and LSTM methods for emotion classification. The result of this study is BERT generates the highest accuracy compared to other methods for the three data scenarios with values of 87.24%, 86.27%, and 86.99% in the first phase. Then, the next accuracy value followed by obtained BiLSTM, and the last is LSTM. In the second phase, BERT also obtained the highest accuracy values for the three data scenarios with values of 94.26%, 93.71 %, and 93.98%. Then, the evaluation using Precision, Recall and F1-Measure results that BERT provides the best overall method. In this study, BERT has good performance for emotion classification.

Traditional topic modeling approaches generally rely on document-term co-occurrence statistics to find latent topics in a collection of documents. However, relying only on such statistics can yield incoherent or hard to interpret results for the end-users in many applications where the interest lies in interpreting the resulting topics (e.g. labeling documents, comparing corpora, guiding content exploration, etc.). In this work, we propose to leverage external common sense knowledge, i.e. information from the real world beyond word co-occurrence, to find topics that are more coherent and more easily interpretable by humans. We introduce the Common Sense Topic Model (CSTM), a novel and efficient approach that augments clustering with knowledge extracted from the ConceptNet knowledge graph. We evaluate this approach on several datasets alongside commonly used models using both automatic and human evaluation, and we show how it shows superior affinity to human judgement. The code for the experiments as well as the training data and human evaluation are available at https://github.com/D2KLab/CSTM.

Common sense is essential for building intelligent machines. While some commonsense knowledge is explicitly stated in human-generated text and can be learnt by mining the web, much of it is unwritten. It is often unnecessary and even unnatural to write about commonsense facts. While unwritten, this commonsense knowledge is not unseen! The visual world around us is full of structure modeled by commonsense knowledge. Can machines learn common sense simply by observing our visual world? Unfortunately, this requires automatic and accurate detection of objects, their attributes, poses, and interactions between objects, which remain challenging problems. Our key insight is that while visual common sense is depicted in visual content, it is the semantic features that are relevant and not low-level pixel information. In other words, photorealism is not necessary to learn common sense. We explore the use of human-generated abstract scenes made from clipart for learning common sense. In particular, we reason about the plausibility of an interaction or relation between a pair of nouns by measuring the similarity of the relation and nouns with other relations and nouns we have seen in abstract scenes. We show that the commonsense knowledge we learn is complementary to what can be learnt from sources of text.

This paper focuses on the classification of emotions and polarity in news headlines and it is meant as an exploration of the connection between emotions and lexical semantics. We first describe the construction of the data set used in evaluation exercise “Affective Text” task at SemEval 2007, annotated for six basic emotions: anger, disgust, fear, joy, sadness and surprise, and for positive and negative polarity. We also briefly describe the participating systems and their results. Second, exploiting the same data set, we propose and evaluate several knowledge-based and corpus-based methods for the automatic identification of emotions in text.

An Ensemble Technique to Classify Multi-Class Textual Emotion

Despite the richness and vastness of the common-sense knowledge bases, we argue that common-sense knowledge has to be integrated into the target applications (Text Classification, Dialogue systems, Information Extraction systems, etc.) more effectively. In order to consider this common-sense knowledge in target applications, we propose a deep learning model of common-sense knowledge in Portuguese language, which can be easily coupled in Natural Language Understanding (NLU) systems in order to leverage their performance. More specifically, the model is composed by a neural network LSTM (Long Short Term Memory) that receives a text from the target application, for example, an user message in a dialog, a response to a user tweet, a news text; and selects and learns what is the best set of common-sense relations to return to the target application, which should be considered in the target learning model or system. We implemented the common-sense learning module in two target applications - a Stance Classification system and an End-to-End Dialogue system. In both cases, incorporating the deep learning model improved the results.

Visual commonsense knowledge has received growing attention in the reasoning of long-tailed visual relationships biased in terms of object and relation labels. Most current methods typically collect and utilize external knowledge for visual relationships by following the fixed reasoning path of {subject, object → predicate} to facilitate the recognition of infrequent relationships. However, the knowledge incorporation for such fixed multidependent path suffers from the data set biased and exponentially grown combinations of object and relation labels and ignores the semantic gap between commonsense knowledge and real scenes. To alleviate this, we propose configurable graph reasoning (CGR) to decompose the reasoning path of visual relationships and the incorporation of external knowledge, achieving configurable knowledge selection and personalized graph reasoning for each relation type in each image. Given a commonsense knowledge graph, CGR learns to match and retrieve knowledge for different subpaths and selectively compose the knowledge routed path. CGR adaptively configures the reasoning path based on the knowledge graph, bridges the semantic gap between the commonsense knowledge, and the real-world scenes and achieves better knowledge generalization. Extensive experiments show that CGR consistently outperforms previous state-of-the-art methods on several popular benchmarks and works well with different knowledge graphs. Detailed analyses demonstrated that CGR learned explainable and compelling configurations of reasoning paths.

Zhekun Luo, Shalini Ghosh, Devin Guillory, Keizo Kato, Trevor Darrell, Huijuan Xu. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Cyberbullying (harassment on social networks) is widely recognized as a serious social problem, especially for adolescents. It is as much a threat to the viability of online social networks for youth today as spam once was to email in the early days of the Internet. Current work to tackle this problem has involved social and psychological studies on its prevalence as well as its negative effects on adolescents. While true solutions rest on teaching youth to have healthy personal relationships, few have considered innovative design of social network software as a tool for mitigating this problem. Mitigating cyberbullying involves two key components: robust techniques for effective detection and reflective user interfaces that encourage users to reflect upon their behavior and their choices. Spam filters have been successful by applying statistical approaches like Bayesian networks and hidden Markov models. They can, like Google’s GMail, aggregate human spam judgments because spam is sent nearly identically to many people. Bullying is more personalized, varied, and contextual. In this work, we present an approach for bullying detection based on state-of-the-art natural language processing and a common sense knowledge base, which permits recognition over a broad spectrum of topics in everyday life. We analyze a more narrow range of particular subject matter associated with bullying (e.g. appearance, intelligence, racial and ethnic slurs, social acceptance, and rejection), and construct BullySpace , a common sense knowledge base that encodes particular knowledge about bullying situations. We then perform joint reasoning with common sense knowledge about a wide range of everyday life topics. We analyze messages using our novel AnalogySpace common sense reasoning technique. We also take into account social network analysis and other factors. We evaluate the model on real-world instances that have been reported by users on Formspring, a social networking website that is popular with teenagers. On the intervention side, we explore a set of reflective user-interaction paradigms with the goal of promoting empathy among social network participants. We propose an “air traffic control”-like dashboard, which alerts moderators to large-scale outbreaks that appear to be escalating or spreading and helps them prioritize the current deluge of user complaints. For potential victims, we provide educational material that informs them about how to cope with the situation, and connects them with emotional support from others. A user evaluation shows that in-context, targeted, and dynamic help during cyberbullying situations fosters end-user reflection that promotes better coping strategies.

Multi-source domain adaptation method for textual emotion classification using deep and broad learning

Emotion detection is crucial in various domains, including psychology, health, social sciences, and marketing. Specifically, in psychology, identifying negative emotions in short Spanish texts, such as tweets, is vital for understanding individuals' emotional states. However, this process is challenging because of factors such as lack of context, cultural nuances, and ambiguous expressions. Although much research on emotion classification in tweets has focused on applications such as crisis analysis, mental health monitoring, and affective computing, most of it has been conducted in English, leaving a significant gap in addressing the emotional needs of Spanish-speaking communities. To address this gap, we used a corpus of 12,000 Spanish tweets tagged with Ekman's negative emotions (sadness, anger, fear, and disgust). Traditional features (n-grams of different types and sizes), syntactic n-grams, and combined features were evaluated. Different deep neural networks, including convolutional neural networks, Bidirectional Encoder Representations of Transformers (BERT), and the robust optimized BERT approach called RoBERTa, were implemented and compared with traditional machine learning methods to identify the most effective method. Extensive testing revealed that BERT achieved the best result, with a macro F1 score of 0.9973. Furthermore, we reported the carbon emissions generated during the training of each implemented method. This study makes a unique contribution by focusing on negative emotions in Spanish, leveraging one of the largest and highest-quality corpora available. It stands out for implementing advanced transformers such as RoBERTa and integrating combined and syntactic n-grams in traditional methods. Furthermore, it highlights how parameters, features, and preprocessing significantly influence performance.

Most object detection methods based on remote sensing images are generally dependent on a large amount of high-quality labeled training data. However, due to the slow acquisition cycle of remote sensing images and the difficulty in labeling, many types of data samples are scarce. This makes few-shot object detection an urgent and necessary research problem. In this paper, we introduce a remote sensing few-shot object detection method based on text semantic fusion relation graph reasoning (TSF-RGR), which learns various types of relationships from common sense knowledge in an end-to-end manner, thereby empowering the detector to reason over all classes. Specifically, based on the region proposals provided by the basic detection network, we first build a corpus containing a large number of text language descriptions, such as object attributes and relations, which are used to encode the corresponding common sense embeddings for each region. Then, graph structures are constructed between regions to propagate and learn key spatial and semantic relationships. Finally, a joint relation reasoning module is proposed to actively enhance the reliability and robustness of few-shot object feature representation by focusing on the degree of influence of different relations. Our TSF-RGR is lightweight and easy to expand, and it can incorporate any form of common sense information. Sufficient experiments show that the text information is introduced to deliver excellent performance gains for the baseline model. Compared with other few-shot detectors, the proposed method achieves state-of-the-art performance for different shot settings and obtains highly competitive results on two benchmark datasets (NWPU VHR-10 and DIOR).

Traditional Chinese Medicine (TCM), with its extensive knowledge base documented in ancient texts, offers a unique resource for contemporary drug discovery, particularly in combatting microbial infections. The success of antimalarial drugs like artemisinin and artesunate, derived from the TCM herb Artemisia annua L., exemplifies the potential of TCM-derived small molecules. This rich repository of natural products and intricate molecular structures could reveal novel compounds with unexplored mechanisms of action. Our study employs a multifaceted approach that combines text mining, detailed textual analysis, and modern antibacterial molecular prediction methodologies to unlock the potential of ancient TCM remedies. We use external knowledge maps, which include databases of known bioactive compounds and their targets, to identify promising TCM candidates. This approach leverages both historical texts and contemporary scientific data to explore the therapeutic potential of TCM. We discovered that herb patterns DiYu→ZeXie and Kushen→ShengJiang potentially combat both Grams-positive and Grams-negative bacteria. We utilized the AntiBac-Pred online tool to identify and analyze the chemical components of herbs, integrating data from ancient texts and TCMDB@Taiwan external knowledge graph. The DiYu→ZeXie groups showed antimicrobial potential against resistant Staphylococcus simulans, while the Kushen→ShengJiang groups exhibited dual antimicrobial effects against Bacillus subtilis. Exploring TCM's extensive repository offers numerous opportunities for discovering therapeutically active compounds. Our synergistic approach, which combines ancient wisdom with modern science, holds significant promise for enhancing our ability to combat infectious diseases. This method could pave the way for a new era of personalized medicine, addressing the urgent need for innovative treatments against multidrug-resistant bacteria and viruses.