scholarly journals SpotFake+: A Multimodal Framework for Fake News Detection via Transfer Learning (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13915-13916 ◽  
Author(s):  
Shivangi Singhal ◽  
Anubha Kabra ◽  
Mohit Sharma ◽  
Rajiv Ratn Shah ◽  
Tanmoy Chakraborty ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Contextual Information ◽  
Full Length ◽  
Multimodal Approach ◽  
Fake News ◽  
Online Platforms ◽  
Multiple Modality ◽  
Substantial Rise ◽  
Single Modality

In recent years, there has been a substantial rise in the consumption of news via online platforms. The ease of publication and lack of editorial rigour in some of these platforms have further led to the proliferation of fake news. In this paper, we study the problem of detecting fake news on the FakeNewsNet repository, a collection of full length articles along with associated images. We present SpotFake+, a multimodal approach that leverages transfer learning to capture semantic and contextual information from the news articles and its associated images and achieves the better accuracy for fake news detection. To the best of our knowledge, this is the first work that performs a multimodal approach for fake news detection on a dataset that consists of full length articles. It outperforms the performance shown by both single modality and multiple-modality models. We also release the pretrained model for the benefit of the community.

Contextual information in terminological knowledge bases: A multimodal approach

2010 ◽  
Vol 42 (7) ◽  
pp. 1928-1950 ◽  
Author(s):  
Arianne Reimerink ◽  
Mercedes García de Quesada ◽  
Silvia Montero-Martínez
Keyword(s):  
Contextual Information ◽  
Knowledge Bases ◽  
Multimodal Approach

scholarly journals A Multimodal Approach to Predict Social Media Popularity

2018 ◽  
Author(s):  
Mayank Meghawat ◽  
Satyendra Yadav ◽  
Debanjan Mahata ◽  
Yifang Yin ◽  
Rajiv Ratn Shah ◽  
...  
Keyword(s):  
Social Media ◽  
Contextual Information ◽  
Primary Sources ◽  
Training Dataset ◽  
Grand Challenge ◽  
Multimodal Approach ◽  
Comparable Performance ◽  
Social Media Platforms ◽  
Data Source ◽  
Popularity Prediction

Multiple modalities represent different aspects by whichinformation 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. Specifically, 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 confirm that despite our multimodalapproach uses the half of the training dataset from SMP-T1, it achieves comparable performance with that of state-of-the-art.

scholarly journals Transfer learning and GRU-CRF augmentation for COVID-19 fake news detection

2021 ◽  
pp. 53-53
Author(s):  
Andrea Karnyoto ◽  
Chengjie Sun ◽  
Bingquan Liu ◽  
Xiaolong Wang
Keyword(s):  
Political Parties ◽  
Transfer Learning ◽  
Hybrid Model ◽  
The Internet ◽  
Online Media ◽  
Fake News ◽  
Baseline Model

The spread of fake news on online media is very dangerous and can lead to casualties, effects on psychology, character assassination, elections for political parties, and state chaos. Fake news that concerning Covid-19 massively spread during the pandemic. Detecting misinformation on the Internet is an essential and challenging task since humans face difficulty detecting fake news. We applied BERT and GPT2 as pre-trained using the BiGRU-Att-CapsuleNet model and BiGRU-CRF features augmentation to solve Fake News detection in Constraint @ AAAI2021 - COVID19 Fake News Detection in English Dataset. This research proved that our hybrid model with augmentation got better accuracy compared to our baseline model. It also showed that BERT gave a better result than GPT2 in all models; the highest accuracy we achieved for BERT is 0.9196, and GPT2 is 0.8986.

scholarly journals Combined treatment modalities in atrophic acne scars: a prospective study

2019 ◽  
Vol 5 (2) ◽  
pp. 243
Author(s):  
Saravanan Narayanan ◽  
Kamalanathan Nallu ◽  
Sridhar Venu ◽  
Arul Raja Ganapathi
Keyword(s):  
Acne Vulgaris ◽  
Combined Treatment ◽  
Treatment Session ◽  
Treatment Modalities ◽  
Multimodal Approach ◽  
Acne Scars ◽  
Pre Treatment ◽  
Grade 3 ◽  
A Prospective Study ◽  
Single Modality

<p class="abstract"><strong>Background:</strong> Atrophic acne scars are one of the sequalae that follows acne vulgaris. These scars are big cosmetic concern presenting with varied morphology like ice-pick, rolling and boxcar scars and it needs multimodal approach to treat effectively rather than a single modality. Our main aim is to study the efficacy of combination therapy using subcision, micro-needling and trichloro acetic acid chemical reconstruction of skin scars (TCA CROSS) in a sequential manner for the management of atrophic acne scars.</p><p class="abstract"><strong>Methods:</strong> Total 30 patients of either sex with grade 2, 3, and 4 atrophic acne scars were graded using Goodman and Baron qualitative grading and were enrolled in the study. After single sitting of subcision, micro-needling and 50% TCA CROSS were performed alternatively at 3 weeks interval for a total of 3 sessions of each. Grading of acne scars were done by taking photographs at pre-treatment, post treatment, 1st and 3rd month after last treatment session.<strong></strong></p><p class="abstract"><strong>Results:</strong> Out of 14 patients with grade 4 acne scars, 9 (64.3%) patients improved to grade 2 and 5 (35.7%) patients improved to Grade 3. Out of 10 patients with Grade 3 scars, 6 (60%) patients improved to grade 1, and 4 (40%) patients were improved to grade 2 at the end of study. All 5 patients with Grade 2 scars showed significant improvement from baseline.</p><p class="abstract"><strong>Conclusions:</strong> Subcision, micro-needling and TCA CROSS, if they are combined and adequately done in proper manner will have excellent response in all types of atrophic acne scars.</p>

scholarly journals Detecting Fake News using Machine Learning: A Systematic Literature Review

2021 ◽  
Vol 58 (1) ◽  
pp. 1932-1939
Author(s):  
Alim Al Ayub Ahmed Et al.
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Political Party ◽  
Fake News ◽  
Machine Learning Classifiers ◽  
Online Platforms ◽  
Learning Classifiers ◽  
Social Media Platforms

Internet is one of the important inventions and a large number of persons are its users. These persons use this for different purposes. There are different social media platforms that are accessible to these users. Any user can make a post or spread the news through these online platforms. These platforms do not verify the users or their posts. So some of the users try to spread fake news through these platforms. These fake news can be a propaganda against an individual, society, organization or political party. A human being is unable to detect all these fake news. So there is a need for machine learning classifiers that can detect these fake news automatically. Use of machine learning classifiers for detecting the fake news is described in this systematic literature review.

scholarly journals On Reinforcement Learning for Full-Length Game of StarCraft

2019 ◽  
Vol 33 ◽  
pp. 4691-4698 ◽  
Author(s):  
Zhen-Jia Pang ◽  
Ruo-Ze Liu ◽  
Zhou-Yu Meng ◽  
Yi Zhang ◽  
Yang Yu ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Transfer Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
Full Length ◽  
Action Space ◽  
Hierarchical Architecture ◽  
Difficulty Level ◽  
Future Research ◽  
Grand Challenge

StarCraft II poses a grand challenge for reinforcement learning. The main difficulties include huge state space, varying action space, long horizon, etc. In this paper, we investigate a set of techniques of reinforcement learning for the full-length game of StarCraft II. We investigate a hierarchical approach, where the hierarchy involves two levels of abstraction. One is the macro-actions extracted from expert’s demonstration trajectories, which can reduce the action space in an order of magnitude yet remain effective. The other is a two-layer hierarchical architecture, which is modular and easy to scale. We also investigate a curriculum transfer learning approach that trains the agent from the simplest opponent to harder ones. On a 64×64 map and using restrictive units, we train the agent on a single machine with 4 GPUs and 48 CPU threads. We achieve a winning rate of more than 99% against the difficulty level-1 built-in AI. Through the curriculum transfer learning algorithm and a mixture of combat model, we can achieve over 93% winning rate against the most difficult noncheating built-in AI (level-7) within days. We hope this study could shed some light on the future research of large-scale reinforcement learning.

scholarly journals "Die-Hard Supporters"

2021 ◽  
Vol 14 (2) ◽  
pp. 86-118
Author(s):  
Danna Aranda
Keyword(s):  
Social Media ◽  
Public Opinion ◽  
Thematic Analysis ◽  
Group Behavior ◽  
Media Campaign ◽  
Fake News ◽  
Networked System ◽  
Online Platforms ◽  
2016 Election ◽  
Group Members

The success of the maverick politician Rodrigo Duterte in the 2016 election is cited as a result of the weaponization of social media—whereby professional, tech-savvy strategists mobilized public opinion through a networked system of disinformation. Yet, there is evidence of grassroots campaign support that emerged via online platforms. Those who have mobilized include Overseas Filipino Workers (OFWs), who have used Facebook groups to rally in support of Duterte. This research looks at the activities of two OFW Facebook groups to understand precisely how and why they organized for Duterte. Employing a dualstage thematic analysis on posts and comments by group members between March 28 – May 9, 2016, three key findings emerged. First, motivations for supporting Duterte varied greatly among users and are far more complex than Duterte’s mandate to crack-down on corruption, crime, and drugs. Second, group behavior deviates from top-heavy explanations of online campaign mobilization, as these groups operated autonomously from Duterte’s official campaign. Finally, these groups were not amorphous and had, as the most active members and organizers, certain intermediaries. These grassroots intermediaries sought to amplify support for Duterte by organizing events, using diversionary tactics, and helping to propagate fake news. These findings suggest that while these groups were operating independently, they were not devoid of influence from Duterte’s official social media campaign.

scholarly journals A Fine-Tuned BERT-Based Transfer Learning Approach for Text Classification

2022 ◽  
Vol 2022 ◽  
pp. 1-17
Author(s):  
Rukhma Qasim ◽  
Waqas Haider Bangyal ◽  
Mohammed A. Alqarni ◽  
Abdulwahab Ali Almazroi
Keyword(s):  
Data Mining ◽  
Social Media ◽  
Transfer Learning ◽  
Language Processing ◽  
Text Classification ◽  
Hate Speech ◽  
Classification Problem ◽  
Learning Approaches ◽  
Fake News ◽  
Targeted Marketing

Text Classification problem has been thoroughly studied in information retrieval problems and data mining tasks. It is beneficial in multiple tasks including medical diagnose health and care department, targeted marketing, entertainment industry, and group filtering processes. A recent innovation in both data mining and natural language processing gained the attention of researchers from all over the world to develop automated systems for text classification. NLP allows categorizing documents containing different texts. A huge amount of data is generated on social media sites through social media users. Three datasets have been used for experimental purposes including the COVID-19 fake news dataset, COVID-19 English tweet dataset, and extremist-non-extremist dataset which contain news blogs, posts, and tweets related to coronavirus and hate speech. Transfer learning approaches do not experiment on COVID-19 fake news and extremist-non-extremist datasets. Therefore, the proposed work applied transfer learning classification models on both these datasets to check the performance of transfer learning models. Models are trained and evaluated on the accuracy, precision, recall, and F1-score. Heat maps are also generated for every model. In the end, future directions are proposed.

scholarly journals Multimodal news analytics using measures of cross-modal entity and context consistency

2021 ◽  
Author(s):  
Eric Müller-Budack ◽  
Jonas Theiner ◽  
Sebastian Diering ◽  
Maximilian Idahl ◽  
Sherzod Hakimov ◽  
...  
Keyword(s):  
Real World ◽  
State Of The Art ◽  
Multimodal Approach ◽  
Entity Linking ◽  
Fake News ◽  
Misleading Information ◽  
Named Entity ◽  
Multimodal Information ◽  
The World ◽  
The Cross

AbstractThe World Wide Web has become a popular source to gather information and news. Multimodal information, e.g., supplement text with photographs, is typically used to convey the news more effectively or to attract attention. The photographs can be decorative, depict additional details, but might also contain misleading information. The quantification of the cross-modal consistency of entity representations can assist human assessors’ evaluation of the overall multimodal message. In some cases such measures might give hints to detect fake news, which is an increasingly important topic in today’s society. In this paper, we present a multimodal approach to quantify the entity coherence between image and text in real-world news. Named entity linking is applied to extract persons, locations, and events from news texts. Several measures are suggested to calculate the cross-modal similarity of the entities in text and photograph by exploiting state-of-the-art computer vision approaches. In contrast to previous work, our system automatically acquires example data from the Web and is applicable to real-world news. Moreover, an approach that quantifies contextual image-text relations is introduced. The feasibility is demonstrated on two datasets that cover different languages, topics, and domains.

Sign in / Sign up

Export Citation Format

Share Document