Content Filtering Research Articles

College Forums with Alumni Based on Content Filtering

College Forums with Alumni Based on Content Filtering

Penguatan Sosiologi Keluarga Di Dunia Digital: Studi Literasi Pengasuhan Anak Usia Dini Berbasis Keluarga

The role in child development in the digital era, the digital era is very influential on a child's development in terms of positive and negative impacts and where there is a very high increase in technological developments that affect the style and lifestyle of children in the digital era.Of course the role of parents in this case is very important due to the impact of the acceleration of technology which is very increasing so that access is very easy, so the role of a parent in this case to supervise a child in using technology in the digital era is never separated from related objects related to access to an internet. The research method in this study is to use literacy studies related to parenting in the advanced era and take case examples from various sources in Indonesia in the last 10 years with an approach from Leedy which focuses on synthesizing between data to obtain relean results and criticize the data which aims as a search for new sources of knowledge on certain social problems, especially on the role of parents and children. The result is that there are three main indicators in positioning parents in dealing with Generation Z, namely as content filters, as technology mentors, and as positive models in early childhood. In addition, authoritative parenting is found to provide limits to children about good and bad things, encourage children's creativity so that children can be adaptive to technology, introduce digital literacy, and collaborative processes with third parties in the form of schools, tutoring, children's social spaces, and informal institutions.

Enhancing multimedia management: cloud-based movie type recognition with hybrid deep learning architecture

Film and movie genres play a pivotal role in captivating relevant audiences across interactive multimedia platforms. With a focus on entertainment, streaming providers are increasingly prioritizing the automatic generation of movie genres within cloud-based media services. In service management, the integration of a hybrid convolutional network proves to be instrumental in effectively distinguishing between a diverse array of video genres. This classification process not only facilitates more refined recommendations and content filtering but also enables targeted advertising. Furthermore, given the frequent amalgamation of components from various genres in cinema, there arises a need for social media networks to incorporate real-time video classification mechanisms for accurate genre identification. In this study, we propose a novel architecture leveraging deep learning techniques for the detection and classification of genres in video films. Our approach entails the utilization of a bidirectional long- and short-term memory (BiLSTM) network, augmented with video descriptors extracted from EfficientNet-B7, an ImageNet pre-trained convolutional neural network (CNN) model. By employing BiLSTM, the network acquires robust video representations and proficiently categorizes movies into multiple genres. Evaluation on the LMTD dataset demonstrates the substantial improvement in the performance of the movie genre classifier system achieved by our proposed architecture. Notably, our approach achieves both computational efficiency and precision, outperforming even the most sophisticated models. Experimental results reveal that EfficientNet-BiLSTM achieves a precision rate of 93.5%. Furthermore, our proposed architecture attains state-of-the-art performance, as evidenced by its F1 score of 0.9012.

Recognizing online video genres using ensemble deep convolutional learning for digital media service management

It's evident that streaming services increasingly seek to automate the generation of film genres, a factor profoundly shaping a film's structure and target audience. Integrating a hybrid convolutional network into service management emerges as a valuable technique for discerning various video formats. This innovative approach not only categorizes video content but also facilitates personalized recommendations, content filtering, and targeted advertising. Given the tendency of films to blend elements from multiple genres, there is a growing demand for a real-time video classification system integrated with social media networks. Leveraging deep learning, we introduce a novel architecture for identifying and categorizing video film genres. Our approach utilizes an ensemble gated recurrent unit (ensGRU) neural network, effectively analyzing motion, spatial information, and temporal relationships. Additionally,w we present a sophisticated deep neural network incorporating the recommended GRU for video genre classification. The adoption of a dual-model strategy allows the network to capture robust video representations, leading to exceptional performance in multi-class movie classification. Evaluations conducted on well-known datasets, such as the LMTD dataset, consistently demonstrate the high performance of the proposed GRU model. This integrated model effectively extracts and learns features related to motion, spatial location, and temporal dynamics. Furthermore, the effectiveness of the proposed technique is validated using an engine block assembly dataset. Following the implementation of the enhanced architecture, the movie genre categorization system exhibits substantial improvements on the LMTD dataset, outperforming advanced models while requiring less computing power. With an impressive F1 score of 0.9102 and an accuracy rate of 94.4%, the recommended model consistently delivers outstanding results. Comparative evaluations underscore the accuracy and effectiveness of our proposed model in accurately identifying and classifying video genres, effectively extracting contextual information from video descriptors. Additionally, by integrating edge processing capabilities, our system achieves optimal real-time video processing and analysis, further enhancing its performance and relevance in dynamic media environments.

Use of Digital Technologies: Family Perspectives on Children's Health

The increasing use of digital technologies among children and adolescents prompts concerns about their impact on development and necessitates family mediation. This study explored primary caregivers’ views on the effects of screen exposure on child health through a focus group with 20 caregivers (17 mothers and 3 grandmothers, aged 20 to 40) from an elementary school in Irecê, Bahia. Findings indicate that children’s screen time, including TV and mobile phones, often lacks proper time and content control due to caregivers’ extensive responsibilities such as remote work and household chores. Major concerns were exposure to violent games, deceptive online profiles, and potential interactions with abusers. Notable behavioral issues in children included irritability, aggression, and sleep problems. Caregivers implemented mediation strategies like setting rules, time restrictions, content filters, and discussing digital self-care. The discussion also addressed addiction mechanisms, family screen habits, gender differences in electronic device usage, and their health impacts on children. An agreement was made to limit screen use across the family, especially an hour before bedtime, aiming to enhance children’s sleep quality and thereby improve their mood and academic performance. This condensed study underscores the challenges caregivers face with children’s digital access and stresses the importance of effective mediation strategies. Enhanced parental engagement and school collaboration are crucial for fostering healthier digital habits that benefit children’s health and family well-being.

The War in Ukraine Through the Prism of Visual Disinformation and the Limits of Specialized Fact-Checking. A Case-Study at Le Monde

The Russian invasion of Ukraine in February 2022 led to a flood of disinformation circulating online, making fact-checking and verification crucial for journalists covering the conflict. Based on five semi-structured interviews and an analysis of 48 debunks published between February and October 2022, this study aims to understand how Les Décodeurs, the fact-checking unit of the French daily newspaper Le Monde, organized its practices in response to the flow of visual disinformation surrounding the conflict, and to place them within the broader framework of practices and categorizations of previous research on fact-checking and disinformation. The findings show that most fact-checks focuses on authentic images with misleading captions, rather than sophisticated manipulation. Previous categorizations prove their ability to describe the 48 pieces of visual disinformation but a more refined approach is suggested by considering visual disinformation as mainly multi-modal. The study reveals the fact-checkers’ role as gatekeepers in filtering content from social networks and addressing the challenge of countering viral disinformation while avoiding unintended amplification. It also identifies a blend of shared and individualized approaches among fact-checking journalists, including manual and pre-digital methods, reflecting the adaptable nature of their work. Based on the latest developments of gatekeeping functions, the study highlights limitations in the challenge of reconciling reactive and retroactive practices with mid-term editorial considerations in a rapidly evolving media ecosystem.

A LETTER FROM SPECIAL EDITION EDITOR IN CHIEF - DR. SHIVA SHANKARAN KR

Dear Readers and Contributors,The Department of Journalism & Mass Communication, Faculty of Science & Humanities, SRM Institute of Science & Technology, Kattankulathur organized a Two- Day National Conference on Journalistic and Creative Freedom: Prospects and Challenges on 21, & 22 September 2023. The conference had eight sessions, including two hybrid mode sessions; the conference has papers across India.The conference included eight different panel experts in the field of our conference themes, such as Press freedom, Media independence, Free speech, Editorial independence, Censorship, Information access, Journalistic ethics, Media pluralism, Artistic expression, Creative autonomy, Freedom of imagination, Intellectual property, Cultural diversity, Creative license, Copyright protection, Artistic integrity, Unrestricted creativity, Online censorship, Social media moderation, Content filtering, Information control, Digital censorship, Content moderation policies, Online speech restrictions, Content removal, Online surveillance. During the research presentation, the experts and participants discussed and cultivated knowledge on the specific topic among the audience.Significantly, the keynote speaker Dr. Debi Chatterjee, Former Professor, Department of International Relations, Jadavpur University, Kolkata, emphasized the role of media in safeguarding democracy in a nation. Transparency and accountability are essential for the functioning of a healthy democracy. Investigative journalism exposes corruption, abuse of power, and other threats to democratic principles. The notable speaker has highlighted the important factor that Media plays a fundamental role in providing citizens with accurate and timely information about political events, policies, and issues. She also asked the media students as well as professionals to be torch bearers for media as well as creative freedom. The valedictory speaker Mr. Nandakummar R, Director, Directorate of Communication, SRM Institute of Science and Technology has incited a diverse and pluralistic media landscape ensures that a variety of perspectives and opinions are represented. And Media diversity is crucial for preventing the concentration of power and fostering a more inclusive democracy.The conference research papers had Sixty-Seven research papers have presented during the two days National conference: Forty-Seven (47) papers on the physical mode and twenty (20) on hybrid mode, including special sessions. Few papers related to scope were selected to be published in the UGC Care-Listed Journal "ShodhKosh: Journal of Visual and Performing Arts" as a special issue titled "National Conference on Journalistic and Creative Freedom: Prospects and Challenges”. I express my sincere thanks to the publisher of Granthaalayah Publications for their noble partnership with our institution, inspiring and acknowledging researchers.

Content Regulation Laws for Chinese ISPs: Legal Responsibilities in Free Speech and Filtering of Harmful Content

This paper delves into the intricate landscape of content regulation laws for Chinese Internet Service Providers (ISPs) and their legal responsibilities concerning free speech and the filtering of harmful content. It offers an in-depth analysis of China’s regulatory framework, delving into the landscape of ISPs in the nation and the evolving legal framework governing content regulation and free speech. Furthermore, the paper explores the responsibilities and obligations of Chinese ISPs in moderating online content. It delves into the complex concept of free speech in the context of China and investigates the government’s role in censorship and content control. The paper highlights the impact of content filtering on free speech and online expression in the Chinese digital landscape. It provides a comprehensive overview of the laws and regulations that define the legal responsibilities of Chinese ISPs, addressing their obligations in monitoring and moderating content. Additionally, it outlines the compliance mechanisms and consequences for non-compliance. The paper emphasizes the implications of these regulations on free speech and online expression, striking a balance between content filtering and the fundamental right to free speech. While the paper refrains from showcasing case studies, it provides public and expert opinions on the impact of content regulation laws. Furthermore, it envisions potential changes in Chinese ISP content regulation laws and conducts a comparative analysis of content regulation practices worldwide, offering recommendations for maintaining a harmonious balance between free speech and content filtering in the digital age.

LANGUAGE DETECTION USING MACHINE LEARNING

This paper presents an innovative Machine Learning (ML) model for language detection that combines the power of logistic regression with a multimodal approach. The proposed model is designed to handle three types of inputs: sequential text data, files, and image representations. The proposed model offers a versatile and accurate solution for identifying languages across diverse data modalities. The model architecture employs logistic regression to enhance interpretability and feature extraction from each input modality. Trained on a comprehensive multilingual dataset, the model exhibits robust performance, showcasing its applicability to real-world scenarios. The model’s ability to process text, files, and images makes it well-suited for applications in content filtering, cross-modal information retrieval, and multilingual sentiment analysis. This research contributes to the advancement of language detection models by offering a unified solution for handling diverse input types.

An analytical approach for the analysis of stress wave transmission and reflection in waveguide systems based on Timoshenko beam theory

The paper presents an analytical continuous solution for the analysis of wave refraction and transmission/reflection caused by arbitrarily complex waveguide subsystems. It allows analyzing the way stress wave components are altered as they go through a substructure. The method is new in that it investigates the wave phenomena which govern the dynamic behavior of a structural system explicitly and studies the effectiveness of different serrated and fractal subsystem designs functioning as wave content filters. Timoshenko beam theory is used to model stress wave propagation in waveguides because of its accuracy and consistency over a wide range of vibration frequencies. The versatility of the method is demonstrated using a number of numerical examples characterizing stress wave refraction in single input/single output and single input/multiple output subsystems to study periodic, fractal, and serrated forms. The low computation cost and stable accuracy of the method over a very wide range of frequencies, make it an effective tool for metaheuristic optimization approaches which require massive calculations over many generations. The method is demonstrated to perform seamlessly in coupling with a genetic algorithm optimization framework to determine the optimal serrated configuration of a wave filter.

Justifying the selection of a neural network linguistic classifier

The subject matter of this article revolves around the exploration of neural network architectures to enhance the accuracy of text classification, particularly within the realm of natural language processing. The significance of text classification has grown notably in recent years due to its pivotal role in various applications like sentiment analysis, content filtering, and information categorization. Given the escalating demand for precision and efficiency in text classification methods, the evaluation and comparison of diverse neural network models become imperative to determine optimal strategies. The goal of this study is to address the challenges and opportunities inherent in text classification while shedding light on the comparative performance of two well-established neural network architectures: Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). To achieve the goal, the following tasks were solved: a comprehensive analysis of these neural network models was performed, considering several key aspects. These aspects include classification accuracy, training and prediction time, model size, data distribution, and overall ease of use. By systematically assessing these attributes, this study aims to provide valuable information about the strengths and weaknesses of each model and enable researchers and practitioners to make informed decisions when selecting a neural network classifier for text classification tasks. The following methods used are a comprehensive analysis of neural network models, assessment of classification accuracy, training and prediction time, model size, and data distribution. The following results were obtained: The LSTM model demonstrated superior classification accuracy across all three training sample sizes when compared to CNN. This highlights LSTM's ability to effectively adapt to diverse data types and consistently maintain high accuracy, even with substantial data volumes. Furthermore, the study revealed that computing power significantly influences model performance, emphasizing the need to consider available resources when selecting a model. Conclusions. Based on the study's findings, the Long Short-Term Memory (LSTM) model emerged as the preferred choice for text data classification. Its adeptness in handling sequential data, recognizing long-term dependencies, and consistently delivering high accuracy positions it as a robust solution for text analysis across various domains. The decision is supported by the model's swift training and prediction speed and its compact size, making it a suitable candidate for practical implementation.

Research and development of a cross-platform application for watching movies and TV series with Chat GPT AI integration

The article presents the results of the research and development of a cross-platform application for watching movies and TV series with Chat GPT AI integration. In today's world, choosing movies and TV series is becoming increasingly difficult due to the huge amount of content available. Users are looking for tools that will help them find and enjoy interesting films and TV series. The main contribution of this article is the presentation of a developed cross-platform application that combines the ability to watch movies and TV series with ChatGPT artificial intelligence. The app provides unique features including powerful search and content filtering, personalized recommendations based on user preferences, and the ability to interact with ChatGPT for recommendations and communication. We take an in-depth look at key aspects of the app, including its functionality and user interface, and provide technical details and solutions used in development. Particular attention is paid to machine learning technologies and algorithms used to improve the quality of recommendations and enrich the user experience. This article not only introduces the entertainment aspect, but also demonstrates how combining entertainment and artificial intelligence can make the user experience in the world of streaming content more interesting and satisfying. We invite readers to review the research details and technological aspects of this innovative project.

ACF-net: appearance-guided content filter network for video captioning

ACF-net: appearance-guided content filter network for video captioning

STUDENT COMMUNITY LEARNING PLATFORM

Abstract- The main aim of this survey paper is to study and figure out the various methods and functionalities to implement an online platform where students of a particular college can share their projects and research done on any particular technology over a secure network which is locally hosted and is accessible to students and staff of a particular institution. The motto behind the project is to help build an interactive student/staff community where each user is able to showcase their talents and knowledge gained over an online platform. The content that can be uploaded ranges from any personal project, project ideas, blogs on new technology learnt or any research done on any topics. This paper covers the various Filtering algorithms & Server hosting. Towards the end of the paper, the future scopes are also discussed. Keywords- Content Filtering, MySQL,PHP, Machine Learning, Student Community, Learning Platform

Accelerating Pattern Matching Using a Novel Multi-Pattern-Matching Algorithm on GPU

Nowadays, almost all network traffic is encrypted. Attackers hide themselves using this traffic and attack over encrypted channels. Inspections performed only on packet headers and metadata are insufficient for detecting cyberattacks over encrypted channels. Therefore, it is important to analyze packet contents in applications that require control over payloads, such as content filtering, intrusion detection systems (IDSs), data loss prevention systems (DLPs), and fraud detection. This technology, known as deep packet inspection (DPI), provides full control over the communication between two end stations by keenly analyzing the network traffic. This study proposes a multi-pattern-matching algorithm that reduces the memory space and time required in the DPI pattern matching compared to traditional automaton-based algorithms with its ability to process more than one packet payload character at once. The pattern-matching process in the DPI system created to evaluate the performance of the proposed algorithm (PA) is conducted on the graphics processing unit (GPU), which accelerates the processing of network packets with its parallel computing capability. This study compares the PA with the Aho-Corasick (AC) and Wu–Manber (WM) algorithms, which are widely used in the pattern-matching process, considering the memory space required and throughput obtained. Algorithm tables created with a dataset containing 500 patterns use 425 and 688 times less memory space than those of the AC and WM algorithms, respectively. In the pattern-matching process using these tables, the PA is 3.5 and 1.5 times more efficient than the AC and WM algorithms, respectively.

Improving Indic code-mixed to monolingual translation using Mixed Script Augmentation, Generation & Transfer Learning

The use of code-mixed languages (written in Roman character) on social media platforms is prevalent in multilingual nations. Translation from code-mixed to monolingual is necessary for social media analysis, content filtering, and targeted advertising. Training translation models from scratch is difficult due to the scarcity of available code-mixed resources and the extremely noisy nature of real-time code-mixed sentences. At the moment, multilingual state-of-the-art language models are routinely used for multilingual applications. However, multilingual models are ineffective in handling code-mixed sentences as it is usually written in Roman script but contain words from at least two languages. In the paper, two data augmentation techniques are proposed to improve code-mixed to monolingual translation, one based on script augmentation and the other on code-mixed sentence generation. The proposed approach converts the code-mixed sentences into ‘Mixed Script form’ that restore the native language words in the sentences with corresponding native language scripts. The novelty of the work is that the multilingual language models include each language’s linguistic competence, preserving context in the monolingual sentences, not possible in the earlier models. Using an mT5 model, denoising and mixed-script switching are performed, followed by monolingual translation with another mT5 model. Code-mixed sentences are generated by employing a simple code-mixed sentence generating technique using monolingual parallel inputs. Two different Indic language sets, namely Hindi-English and Bengali-English are applied and in each case, the proposed approach outperforms straight uni-script (Roman) code-mixed to monolingual translation.

Audio-Visual Based Arabic Learning Through Social Media: Youtube, Tiktok, Instagram, Facebook

Arabic language learning in the digital era that demands global communication skills that students must have, teachers need to use social media in audio-visual based learning such as Youtube, Tiktok, Instagram and Facebook. The use of social media has an influence in audio-visual based Arabic language learning, namely: increasing learning motivation, improving listening skills, increasing vocabulary mastery, improving speaking skills, easily accessible, and increasing creativity. Although social media has influence and advantages, it also has disadvantages that must be anticipated. The most prominent drawback of social media is the presence of negative audio-visual content that is not worth showing to students. Therefore, teachers must be qualified facilitators in filtering content so that teaching materials on social media are in accordance with learning objectives.

Limited knowledge and informal lobbying: internet regulation through content filters in Swedish public libraries

PurposeThe purpose of this paper is to describe and explore the current state of internet regulation through content filters in Swedish public libraries.Design/methodology/approachData was collected through an electronic survey directed to library managers of Sweden’s 290 main municipal libraries. 164 answers were returned, yielding a 57% response rate. The analysis comprises descriptive statistics for quantitative data and an activity theory approach with focus on contradictions for qualitative counterparts.FindingsIn total, 33% of the responding libraries report having content filters; 50% have not; and a surprising 18% do not know. There is a strong correlation between internet misuse and positive attitudes towards filters, and, reversely, between lack of misuse and lack of active stances concerning filters. Rather than seeing this as weakness, the authors suggest that there is strength in a context-bound flexibility open to practical experience and weighting of values, ethics, legislation and local circumstances. More troublesome indications concern the high deferral of decision-making to local authorities (municipalities) whereby libraries are left with limited insight and influence.Research limitations/implicationsThe situation calls for professional organisations to address political mandate questions, and educational programs to strengthen future information professionals’ knowledge of IT in general; filter issues in specific; and local authority decision-making. The study highlights the need of adequate information professional competences and mandates to decide on and oversee internet regulation.Originality/valueTo the best of the authors’ knowledge, this is the first internationally published study on content filters in Swedish public libraries.

Use of Social Media for Patient Education in Dermatology: Narrative Review.

Social media has rapidly become one of the main avenues for news and communication among those with access to technology. Nearly 60% or 4.7 billion people worldwide use social media. Different social media networks provide users with a barrage of posts, opinions, and transformations. With this noticeable uptick in physician and patient education usage of social media, exploration of the impacts of social media on patient education in dermatology is crucial. The goal of this narrative review was to evaluate existing peer-reviewed literature examining the use of social media for patient education in dermatology and to establish trends and implications. Additional attention was given to different social media sites, and potential differences in modalities of posts such as short-form videos on TikTok and Instagram Reels, long-form videos on YouTube, and infographics on Twitter, Instagram, and Facebook. PubMed, Access DermatologyDxRx, and Scopus searches of peer-reviewed publications were performed to discover articles with social media and patient education keywords in combination with other health care-relevant or dermatology-relevant keywords. Subsequently, the screening of these studies was performed by the author who has experience with education and research experience in health care, dermatology, social media, and telehealth. Ultimately, the selected articles were summarized through qualitative analysis of key points and presented for further discussion. Through this narrative review, the researcher was able to identify several publications focusing on dermatology and social media. Some common subject areas included the use of social media for the promotion of private dermatology practices, residency programs, and research journals. So long as providers, such as dermatologists, take ethical considerations into account, these platforms can provide patients with curated educational content. In addition, several publications emphasized the use of social media as a form of patient education on dermatologic conditions but also as a source of misinformation. This narrative review illuminated the use of social media as a form of patient education for dermatology, with its applications addressed across many demographics and situations. As social media platforms continue to update their algorithms, content filters, and posts, social media may become a reputable form of patient education in dermatology. Future studies and innovations should continue to explore innovations in this space, the efficacy of different modalities of posts, and longitudinal differences in patient outcomes and health literacy.

Detecting Images with Adult Content Using SURF and Haar Wavelet

Detecting images with adult content is one of the necessary and challenging problems in the fields of machine learning and machine vision. It can be used for a variety of applications such as content filtering and censoring, and user tracking, and banning