STLC-KG:A Social Text Steganalysis Method Combining Large-Scale Language Models and Common-Sense Knowledge Graphs

Commonsense inference poses a unique challenge to reason and generate the physical, social, and causal conditions of a given event. Existing approaches to commonsense inference utilize commonsense transformers, which are large-scale language models that learn commonsense knowledge graphs. However, they suffer from a lack of coverage and expressive diversity of the graphs, resulting in a degradation of the representation quality. In this paper, we focus on addressing missing relations in commonsense knowledge graphs, and propose a novel contrastive learning framework called SOLAR . Our framework contrasts sets of semantically similar and dissimilar events, learning richer inferential knowledge compared to existing approaches. Empirical results demonstrate the efficacy of SOLAR in commonsense inference of diverse commonsense knowledge graphs. Specifically, SOLAR outperforms the state-of-the-art commonsense transformer on commonsense inference with ConceptNet by 1.84% on average among 8 automatic evaluation metrics. In-depth analysis of SOLAR sheds light on the effects of the missing relations utilized in learning commonsense knowledge graphs.

A Comprehensive Methodology for Extracting Signal from Social Media Text Using Natural Language Processing and Machine Learning

Background:Understanding complex biological pathways, including gene-gene interactions and gene regulatory networks, is critical for exploring disease mechanisms and drug development. Manual literature curation of biological pathways is useful but cannot keep up with the exponential growth of the literature. Large-scale language models (LLMs), notable for their vast parameter sizes and comprehensive training on extensive text corpora, have great potential in automated text mining of biological pathways.Method:This study assesses the effectiveness of 21 LLMs, including both API-based models and open-source models. The evaluation focused on two key aspects: gene regulatory relations (specifically, ‘activation’, ‘inhibition’, and ‘phosphorylation’) and KEGG pathway component recognition. The performance of these models was analyzed using statistical metrics such as precision, recall, F1 scores, and the Jaccard similarity index.Results:Our results indicated a significant disparity in model performance. Among the API-based models, ChatGPT-4 and Claude-Pro showed superior performance, with an F1 score of 0.4448 and 0.4386 for the gene regulatory relation prediction, and a Jaccard similarity index of 0.2778 and 0.2657 for the KEGG pathway prediction, respectively. Open-source models lagged their API-based counterparts, where Falcon-180b-chat and llama1–7b led with the highest performance in gene regulatory relations (F1 of 0.2787 and 0.1923, respectively) and KEGG pathway recognition (Jaccard similarity index of 0.2237 and 0. 2207, respectively).Conclusion:LLMs are valuable in biomedical research, especially in gene network analysis and pathway mapping. However, their effectiveness varies, necessitating careful model selection. This work also provided a case study and insight into using LLMs as knowledge graphs.

With the rapid development of social networks, short texts have become a prevalent form of social communications on the Internet. Measuring the similarity between short texts is a fundamental task to many applications, such as social network text querying, short text clustering and geographical event detection for smart city. However, short texts in social media always show limited contextual information and they are sparse, noisy and ambiguous. Hence, effectively measuring the distance between short texts is a challenging task.

The Impact of Arabic Part of Speech Tagging on Sentiment Analysis: A New Corpus and Deep Learning Approach

An interesting application for social robots is to act as a presenter, for example as a museum guide. In this paper, we present a fully automated system architecture for building adaptive presentations for embodied agents. The presentation is generated from a knowledge graph, which is also used to track the grounding state of information, based on multimodal feedback from the user. We introduce a novel way to use large-scale language models (GPT-3 in our case) to lexicalise arbitrary knowledge graph triples, greatly simplifying the design of this aspect of the system. We also present an evaluation where 43 participants interacted with the system. The results show that users prefer the adaptive system and consider it more human-like and flexible than a static version of the same system, but only partial results are seen in their learning of the facts presented by the robot.

Despite the increased use of social media and text messaging among adolescents, it is unclear how effective education transmitted via these mechanisms is for reducing sexual risk behavior. Accordingly, we conducted a systematic review of the literature to examine the effectiveness of social media and text messaging interventions designed to increase sexually transmitted disease (STD) knowledge, increase screening/testing, decrease risky sexual behaviors, and reduce the incidence of STDs among young adults aged 15 through 24 years. Eleven studies met our inclusion criteria. Most of the included studies used a control group to explore intervention effects and included both young men and women. Sample sizes ranged from 32 to 7606 participants, and follow-up periods ranged between 4 weeks and 12 months. These studies provide preliminary evidence indicating that social media and text messaging can increase knowledge regarding the prevention of STDs. These interventions may also affect behavior, such as screening/testing for STDs, sexual risk behaviors, and STD acquisition, but the evidence for effect is weak. Many of these studies had several limitations that future research should address, including a reliance on self-reported data, small sample sizes, poor retention, low generalizability, and low analytic rigor. Additional research is needed to determine the most effective and engaging approaches for young men and women.

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.

INTRODUCTION. Building effective communication with the target audience through media texts is a relevant technique of interactive interaction. The correlation of methods of interactive communication with a regional audience and the functional purpose of elements of a social media media text is studied. The purpose of the study is to substantiate the convergence of the functionality of interactive methods of communication with a regional audience in media texts of social media. The theoretical novelty of the work lies in identifying the convergence of the functionality of media texts, in introducing the concept of “landing” of media content into scientific circulation.MATERIALS AND METHODS. The theoretical basis of the study was the works of L.R. Duskaeva, E.A. Zvereva, A.A. Kazakov, N.I. Klushina, A.M. Shesterina on the use of interactive techniques in media texts. The most comprehensive Tambov communities on VKontakte and Telegram channels were selected as an empirical base. The study used the method of content analysis of social media texts for 2023-2024.RESULTS AND DISCUSSION. The following conclusions were formulated in the course of the study: 1) each speech technique performs several functions, which indicates the convergence of the functionality of media texts; 2) speech techniques of interactive communication in synthesis with technical means demonstrate effectiveness; 3) speech techniques are a manipulative means, and technical means are used to implement media communication tasks.CONCLUSION. Interactive speech techniques in media texts allow to influence the user, involve him in the news item and form a certain opinion about it, motivate to leave a social reaction to the media content. This gives the authors the opportunity to make the platform more recognizable and interesting, as well as to increase the effectiveness of the community.

Large-scale language models (LLMs) have basically changed the limits of what can be achieved by natural language processing and this was the case of GPT-3 at its very first demonstration back in 2020. This study outlines in detail their journey. It goes through all the concepts of their architecture. Besides, it describes the training process. The article records the gradual increasing of their volumetry and the consequent differences of their properties along the way. Different methods of testing these models are also indicated. Besides, it refers to their application in various fields. Besides, this research work deals with the advent of multi-modal systems capable of autonomous decision-making. We have centered our work on the landmark research that has been published in the period of 2022–2024. We reckon the self-supervised pre-training, instruction tuning, preference optimization, and reasoning-directed reinforcement learning as four main areas that contributed to the development of LLMs. These approaches have converted LLMs to be no longer just the text generators but rather the most versatile AI systems that they are. Our focus is on their use in the medical field and bioinformatics. We address the challenge of explaining the functioning of large language models (LLMs). We tell the story of in-context learning. We discuss the development of LLMs-based agents. At the end, we are identifying the major limitations of the present-time and, simultaneously, suggesting a few ideas for the future in this fast-evolving area.

LLMCL-GEC: Advancing grammatical error correction with LLM-driven curriculum learning

Social media platforms have become central spaces for young people to engage with a vast array of digital content, significantly influencing their identities, beliefs, and behaviors. By examining think‐aloud and interview data, this study investigated how adolescents conceptualize social media as sources of news, political information, and tools for identity negotiation. The results informed the creation of a conceptual map outlining how the process of information‐seeking occurs through social media texts. Findings revealed a nuanced relationship between young people and social media, with participants conceptualizing social media texts as poor quality, but engaging frequently. While young people demonstrated some awareness of the need to verify content and awareness of algorithmic influences shaping their feeds, they often failed to critically engage with the content, which limited their ability to form a comprehensive understanding of complex issues, potentially hindering their capacity for informed discourse. Data revealed that young people passively interacted with social media texts through the algorithm, though they engaged in reciprocal algorithmic manipulation, where they consciously curated their algorithmic output. This research offers critical insights for educators, policymakers, and social media platforms aiming to foster media literacy and promote informed, responsible digital citizenship amongst youth. Ultimately, the findings emphasize the need for media literacy education to support critical thinking and lateral reading skills, empowering youth to navigate the digital information landscape effectively.

The cinematographic vanguard has historically been important in fostering cinematographic creation and innovation. In the digital age, its study acquires a new dimension of relevance, since the analysis of these vanguard movements provides students with tools to understand how cinema has evolved as a means of artistic expression and social manifestation. This knowledge is essential to developing robust critical thinking, capable of evaluating not only the content of a film, but also its form, its historical context, and its cultural relevance from and in its immediate environment. With the arrival of large-scale language models (LLM) and generative artificial intelligence (IAGen), students face an increasingly complex social landscape where technologies are transforming the production, distribution and analysis of movies. LLMs can generate scripts or critical analyses, while IAGens can create visual effects or even entire film sequences, modifying the cinematic concept. This essay analyzes the importance of cinematic avant-garde in the development of students’ critical thinking, especially in the current context of the proliferation of large-scale language models in the form of generative artificial intelligences.

As the world’s digital population grows, so does the reach and usage of social media: in 2021, 56% of the global population were social media users [1]. Social networks are now a part of our everyday life and continue to transform the way we interact with others on a global scale The downside is that negative behaviors in social interactions are also increasing their presence. For example, between March 1 and April 30, the OBERAXE (Spanish Observatory of Racism and Xenophobia) has detected a 27% increase in hate speech on social networks with respect to the previous two-month period [2]. In this paper we target the detection and classification of sexist content in social media texts. Two tasks are considered: (i) a binary classification task to decide whether a given text is sexist or not; and (ii) a multiclass classification task according to the type of sexism present in it.

Multiple modalities represent different aspects by which information is conveyed by a data source. Modern day social media platforms are one of the primary sources of multimodal data, where users use different modes of expression by posting textual as well as multimedia content such as images and videos for sharing information. Multimodal information embedded in such posts could be useful in predicting their popularity. To the best of our knowledge, no such multimodal dataset exists for the prediction of social media photos. In this work, we propose a multimodal dataset consisiting of content, context, and social information for popularity prediction. Speci?cally, we augment the SMPT1 dataset for social media prediction in ACM Multimedia grand challenge 2017 with image content, titles, descriptions, and tags. Next, in this paper, we propose a multimodal approach which exploits visual features (i.e., content information), textual features (i.e., contextual information), and social features (e.g., average views and group counts) to predict popularity of social media photos in terms of view counts. Experimental results con?rm that despite our multimodal approach uses the half of the training dataset from SMP-T1, it achieves comparable performance with that of state-of-the-art.