scholarly journals Importance-Aware Learning for Neural Headline Editing

2020 ◽  
Vol 34 (05) ◽  
pp. 9282-9289
Author(s):  
Qingyang Wu ◽  
Lei Li ◽  
Hao Zhou ◽  
Ying Zeng ◽  
Zhou Yu
Keyword(s):  
Social Media ◽  
Large Scale ◽  
Network Models ◽  
Language Models ◽  
Neural Network Models ◽  
Generation Task ◽  
Social Media Platforms ◽  
Editing Process ◽  
Different Levels

Many social media news writers are not professionally trained. Therefore, social media platforms have to hire professional editors to adjust amateur headlines to attract more readers. We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers. To train such a neural headline editing model, we collected a dataset which contains articles with original headlines and professionally edited headlines. However, it is expensive to collect a large number of professionally edited headlines. To solve this low-resource problem, we design an encoder-decoder model which leverages large scale pre-trained language models. We further improve the pre-trained model's quality by introducing a headline generation task as an intermediate task before the headline editing task. Also, we propose Self Importance-Aware (SIA) loss to address the different levels of editing in the dataset by down-weighting the importance of easily classified tokens and sentences. With the help of Pre-training, Adaptation, and SIA, the model learns to generate headlines in the professional editor's style. Experimental results show that our method significantly improves the quality of headline editing comparing against previous methods.

scholarly journals Data-to-Text Generation with Content Selection and Planning

2019 ◽  
Vol 33 ◽  
pp. 6908-6915 ◽  
Author(s):  
Ratish Puduppully ◽  
Li Dong ◽  
Mirella Lapata
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Network Models ◽  
Text Generation ◽  
Neural Network Models ◽  
Generation Task ◽  
Content Selection ◽  
End To End ◽  
Two Stages

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

scholarly journals Ensemble Deep Learning on Time-Series Representation of Tweets for Rumor Detection in Social Media

2020 ◽  
Vol 10 (21) ◽  
pp. 7541
Author(s):  
Chandra Mouli Madhav Kotteti ◽  
Xishuang Dong ◽  
Lijun Qian
Keyword(s):  
Social Media ◽  
Time Series ◽  
Series Representation ◽  
Network Models ◽  
Majority Voting ◽  
Neural Network Models ◽  
Fast Detection ◽  
Social Media Platforms ◽  
Verification Process ◽  
Rumor Detection

Social media is a popular platform for information sharing. Any piece of information can be spread rapidly across the globe at lightning speed. The biggest challenge for social media platforms like Twitter is how to trust news shared on them when there is no systematic news verification process, which is the case for traditional media. Detecting false information, for example, detection of rumors is a non-trivial task, given the fast-paced social media environment. In this work, we proposed an ensemble model, which performs majority-voting scheme on a collection of predictions of neural networks using time-series vector representation of Twitter data for fast detection of rumors. Experimental results show that proposed neural network models outperformed classical machine learning models in terms of micro F1 score. When compared to our previous works the improvements are 12.5% and 7.9%, respectively.

SHEDR: An End-to-End Deep Neural Event Detection and Recommendation Framework for Hyperlocal News Using Social Media

2021 ◽  
Author(s):  
Yuheng Hu ◽  
Yili Hong
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Deep Learning ◽  
Event Detection ◽  
Large Scale ◽  
Short Term Memory ◽  
State Of The Art ◽  
Neural Network Models ◽  
Neural Event ◽  
End To End

Residents often rely on newspapers and television to gather hyperlocal news for community awareness and engagement. More recently, social media have emerged as an increasingly important source of hyperlocal news. Thus far, the literature on using social media to create desirable societal benefits, such as civic awareness and engagement, is still in its infancy. One key challenge in this research stream is to timely and accurately distill information from noisy social media data streams to community members. In this work, we develop SHEDR (social media–based hyperlocal event detection and recommendation), an end-to-end neural event detection and recommendation framework with a particular use case for Twitter to facilitate residents’ information seeking of hyperlocal events. The key model innovation in SHEDR lies in the design of the hyperlocal event detector and the event recommender. First, we harness the power of two popular deep neural network models, the convolutional neural network (CNN) and long short-term memory (LSTM), in a novel joint CNN-LSTM model to characterize spatiotemporal dependencies for capturing unusualness in a region of interest, which is classified as a hyperlocal event. Next, we develop a neural pairwise ranking algorithm for recommending detected hyperlocal events to residents based on their interests. To alleviate the sparsity issue and improve personalization, our algorithm incorporates several types of contextual information covering topic, social, and geographical proximities. We perform comprehensive evaluations based on two large-scale data sets comprising geotagged tweets covering Seattle and Chicago. We demonstrate the effectiveness of our framework in comparison with several state-of-the-art approaches. We show that our hyperlocal event detection and recommendation models consistently and significantly outperform other approaches in terms of precision, recall, and F-1 scores. Summary of Contribution: In this paper, we focus on a novel and important, yet largely underexplored application of computing—how to improve civic engagement in local neighborhoods via local news sharing and consumption based on social media feeds. To address this question, we propose two new computational and data-driven methods: (1) a deep learning–based hyperlocal event detection algorithm that scans spatially and temporally to detect hyperlocal events from geotagged Twitter feeds; and (2) A personalized deep learning–based hyperlocal event recommender system that systematically integrates several contextual cues such as topical, geographical, and social proximity to recommend the detected hyperlocal events to potential users. We conduct a series of experiments to examine our proposed models. The outcomes demonstrate that our algorithms are significantly better than the state-of-the-art models and can provide users with more relevant information about the local neighborhoods that they live in, which in turn may boost their community engagement.

Physical Distancing and Social Media Use in Emerging and Older Adults During COVID-19: Large Scale Cross-Sectional and Longitudinal Survey Study (Preprint)

2021 ◽  
Author(s):  
Thabo J van Woudenberg ◽  
Roy Hendrikx ◽  
Moniek Buijzen ◽  
Julia CM van Weert ◽  
Bas van den Putte ◽  
...  
Keyword(s):  
Older Adults ◽  
Social Media ◽  
Emerging Adults ◽  
Large Scale ◽  
Media Use ◽  
Longitudinal Survey ◽  
Social Media Use ◽  
Random Intercept ◽  
Social Media Platforms

BACKGROUND Although emerging adults play a role in the spread of COVID-19, they are less likely to develop severe symptoms after infection. Emerging adults’ relatively high use of social media as source of information raises concerns regarding COVID-19 related behavioral compliance (i.e., physical distancing) in this age group. OBJECTIVE Therefore, the current study investigated physical distancing in emerging adults in comparison to older adults and looked at the role of using social media for COVID-19 news and information in this regard. In addition, this study explored the relation between physical distancing and different social media platforms and sources. METHODS Secondary data of a large-scale national longitudinal survey (N = 123,848, 34.% male) between April and November 2020 were used. Participants indicated, ranging for one to eight waves, how often they were successful in keeping 1.5 meters distance on a 7-point Likert scale. Participants between 18 and 24 years old were considered young adults and older participants were identified as older adults. Also, a dummy variable was created to indicate per wave whether participants used social media for COVID-19 news and information. A subset received follow-up questions asking participants to indicate which platforms they have used and what sources of news and information they had seen on social media. All preregistered hypotheses were tested with Linear Mixed-Effects Models and Random Intercept Cross-Lagged Panel Models. RESULTS Emerging adults reported less physical distancing behaviors than older adults (b = -.08, t(86213.83) = -26.79, p < .001). Also, emerging adults were more likely to use social media for COVID-19 news and information (b = 2.48, SE = .11, Wald = 23.66, p = <.001), which mediated the association with physical distancing, but only to a small extend (indirect effect: b = -0.03, 95% CI = [-0.04; -0.02]). Opposed to our hypothesis, the longitudinal Random Intercept Cross-Lagged Panel Model showed no evidence that physical distancing was predicted by social media use of the previous wave. However, we did find evidence that using social media affected subsequent physical distancing behavior. Moreover, additional analyses showed that most social media platforms (i.e., YouTube, Facebook and Instagram) and interpersonal communication showed negative associations with physical distancing while others platforms (i.e. LinkedIn and Twitter) and Governmental messages showed no to a slightly positive associations with physical distancing. CONCLUSIONS In conclusion, we should be vigilant for physical distancing of emerging adults, but this study give no reason the to worry about the role of social media for COVID-19 news and information. However, as some social media platforms and sources showed negative associations, future studies should more carefully look into these factors to better understand the associations between social media use for news and information, and behavioral interventions in times of crisis.

A shift from science to politics : a content analysis of COVID-19 Videos on YouTube (Preprint)

2021 ◽  
Author(s):  
Chyun-Fung Shi ◽  
Matthew C So ◽  
Sophie Stelmach ◽  
Arielle Earn ◽  
David J D Earn ◽  
...  
Keyword(s):  
Public Health ◽  
Social Media ◽  
Content Analysis ◽  
Large Scale ◽  
Control Measures ◽  
Mitigation Measures ◽  
Health Campaigns ◽  
Public Attention ◽  
Conflicting Information ◽  
Social Media Platforms

BACKGROUND The COVID-19 pandemic is the first pandemic where social media platforms relayed information on a large scale, enabling an “infodemic” of conflicting information which undermined the global response to the pandemic. Understanding how the information circulated and evolved on social media platforms is essential for planning future public health campaigns. OBJECTIVE This study investigated what types of themes about COVID-19 were most viewed on YouTube during the first 8 months of the pandemic, and how COVID-19 themes progressed over this period. METHODS We analyzed top-viewed YouTube COVID-19 related videos in English from from December 1, 2019 to August 16, 2020 with an open inductive content analysis. We coded 536 videos associated with 1.1 billion views across the study period. East Asian countries were the first to report the virus, while most of the top-viewed videos in English were from the US. Videos from straight news outlets dominated the top-viewed videos throughout the outbreak, and public health authorities contributed the fewest. Although straight news was the dominant COVID-19 video source with various types of themes, its viewership per video was similar to that for entertainment news and YouTubers after March. RESULTS We found, first, that collective public attention to the COVID-19 pandemic on YouTube peaked around March 2020, before the outbreak peaked, and flattened afterwards despite a spike in worldwide cases. Second, more videos focused on prevention early on, but videos with political themes increased through time. Third, regarding prevention and control measures, masking received much less attention than lockdown and social distancing in the study period. CONCLUSIONS Our study suggests that a transition of focus from science to politics on social media intensified the COVID-19 infodemic and may have weakened mitigation measures during the first waves of the COVID-19 pandemic. It is recommended that authorities should consider co-operating with reputable social media influencers to promote health campaigns and improve health literacy. In addition, given high levels of globalization of social platforms and polarization of users, tailoring communication towards different digital communities is likely to be essential.

Detailed Simulation of Large Scale Neural Network Models

1997 ◽  
pp. 931-935 ◽  
Author(s):  
Anders Lansner ◽  
Örjan Ekeberg ◽  
Erik Fransén ◽  
Per Hammarlund ◽  
Tomas Wilhelmsson
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Network Models ◽  
Neural Network Models ◽  
Detailed Simulation

scholarly journals “Best of both worlds”: A students-as-partners near-peer moderation program improves student engagement in a course Facebook group

2019 ◽  
Vol 3 (1) ◽  
pp. 169-181
Author(s):  
Mohammad Jay ◽  
Michelle Lim ◽  
Khalid Hossain ◽  
Tara White ◽  
Syed Reza Naqvi ◽  
...  
Keyword(s):  
Social Media ◽  
Student Engagement ◽  
Online Communication ◽  
Traditional Learning ◽  
The Third ◽  
Social Media Platforms ◽  
Effective Use ◽  
Senior Students ◽  
Traditional Learning Environments

Social media platforms like Facebook are designed to facilitate online communication and networking, primarily around content posted by users. As such, these technologies are being considered as potential enhancements to traditional learning environments. However, various barriers to effective use may arise. Our research investigated the effectiveness of a students-as-partners near-peer moderation project, arising from collaboration between instructors and senior students, as a vehicle for enhancing student interaction in a Facebook group associated with a large introductory science course. The quantity and quality of sample posts and comments from Facebook groups from three successive academic years were evaluated using a rubric that considered characteristics such as civility, content accuracy, critical thinking and psychological support. Two of these groups were moderated by near-peer students while the third group was not moderated.  We found improved course discussion associated with moderated groups in addition to benefits to moderators and the faculty partner. This suggests that near-peer moderation programs working in collaboration with faculty may increase student engagement in social media platforms.

scholarly journals Usage and Scaling of an Open-Source Spiking Multi-Area Model of Monkey Cortex

2021 ◽  
pp. 47-59
Author(s):  
Sacha J. van Albada ◽  
Jari Pronold ◽  
Alexander van Meegen ◽  
Markus Diesmann
Keyword(s):  
Open Source ◽  
Large Scale ◽  
Network Models ◽  
Macaque Monkey ◽  
Source Model ◽  
Model Specification ◽  
Data Sets ◽  
Neural Network Models ◽  
Wide Range ◽  
Ict Infrastructure

AbstractWe are entering an age of ‘big’ computational neuroscience, in which neural network models are increasing in size and in numbers of underlying data sets. Consolidating the zoo of models into large-scale models simultaneously consistent with a wide range of data is only possible through the effort of large teams, which can be spread across multiple research institutions. To ensure that computational neuroscientists can build on each other’s work, it is important to make models publicly available as well-documented code. This chapter describes such an open-source model, which relates the connectivity structure of all vision-related cortical areas of the macaque monkey with their resting-state dynamics. We give a brief overview of how to use the executable model specification, which employs NEST as simulation engine, and show its runtime scaling. The solutions found serve as an example for organizing the workflow of future models from the raw experimental data to the visualization of the results, expose the challenges, and give guidance for the construction of an ICT infrastructure for neuroscience.

scholarly journals Demand Modelling in Telecommunications

10.14311/1121 ◽  
2009 ◽  
Vol 49 (2) ◽  
Author(s):  
M. Chvalina
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Network Models ◽  
Short Term ◽  
Neural Network Models ◽  
Term Forecast ◽  
Artificial Intelligence Methods ◽  
Demand Modelling

This article analyses the existing possibilities for using Standard Statistical Methods and Artificial Intelligence Methods for a short-term forecast and simulation of demand in the field of telecommunications. The most widespread methods are based on Time Series Analysis. Nowadays, approaches based on Artificial Intelligence Methods, including Neural Networks, are booming. Separate approaches will be used in the study of Demand Modelling in Telecommunications, and the results of these models will be compared with actual guaranteed values. Then we will examine the quality of Neural Network models. 

Evaluating the quality of argon‐arc welded joints using neural network models with regression input

2000 ◽  
Vol 14 (7) ◽  
pp. 559-564
Author(s):  
E A Gladkov ◽  
A V Maloletkov ◽  
R A Perkovskii ◽  
A I Gavrilov
Keyword(s):  
Neural Network ◽  
Welded Joints ◽  
Network Models ◽  
Neural Network Models
Sign in / Sign up

Export Citation Format

Share Document