Frame Information Research Articles

Combating misinformation with internet culture: the case of Brazilian public health organizations and their COVID-19 vaccination campaigns

Purpose This study investigates the communication behavior of public health organizations on Twitter during the COVID-19 vaccination campaign in Brazil. It contributes to the understanding of the organizational framing of health communication by showcasing several instances of framing devices that borrow from (Brazilian) internet culture. The investigation of this case extends the knowledge by providing a rich description of the organizational framing of health communication to combat misinformation in a politically charged environment.Design/methodology/approach The authors collected a Twitter dataset of 77,527 tweets and analyzed a purposeful subsample of 536 tweets that contained information provided by Brazilian public health organizations about COVID-19 vaccination campaigns. The data analysis was carried out quantitatively and qualitatively by combining social media analytics techniques and frame analysis.Findings The analysis showed that Brazilian health organizations used several framing devices that have been identified by previous literature such as hashtags, links, emojis or images. However, the analysis also unearthed hitherto unknown visual framing devices for misinformation prevention and debunking that borrow from internet culture such as “infographics,” “pop culture references” and “internet-native symbolism.”Research limitations/implications First, the identification of framing devices relating to internet culture add to our understanding of the so far little addressed framing of misinformation combat messages. The case of Brazilian health organizations provides a novel perspective to knowledge by offering a notion of internet-native symbols (e.g. humor, memes) and popular culture references for misinformation combat, including misinformation prevention. Second, this study introduces a frontier of political contextualization to misinformation research that does not relate to the partisanship of the spreaders but that relates to the political dilemmas of public organizations with a commitment to provide accurate information to citizens.Practical implications The findings inform decision-makers and public health organizations about framing devices that are tailored to internet-native audiences and can guide strategies to carry out information campaigns in misinformation-laden social media environments.Social implications The findings of this case study expose the often-overlooked cultural peculiarities of framing information campaigns on social media. The report of this study from a country in the Global South helps to contrast several assumptions and strategies that are prevalent in (health) discourses in Western societies and scholarship.Originality/value This study uncovers unconventional and barely addressed framing devices of health organizations operating in Brazil, which provides a novel perspective to the body of research on misinformation. It contributes to existing knowledge about frame analysis and broadens the understanding of frame devices borrowing from internet culture. It is a call for a frontier in misinformation research that deals with internet culture as part of organizational strategies for successful misinformation combat.

Adaptive undersampling and short clip-based two-stream CNN-LSTM model for surgical phase recognition on cholecystectomy videos

Surgical phase recognition is challenging due to overfitting problems caused by imbalanced data among surgical phases. We proposed an adaptive sampling rate-based undersampling method that could generate the number of each surgical phase data similarly to alleviate biased learning. To improve the performance of our method, we also introduced a two-stream CNN-LSTM model that could extract temporal information on behavioral changes between each image frame. First, we extracted a total of 40,236 short clips using an adaptive subsampling rate from the entire video. Each short clip was entered into a pre-trained GoogLeNet. The output with visual information was then immediately fed into a sequence-to-sequence LSTM model to extract temporal information of neighbor frames within a short clip. At the same time, another sequence-to-vector LSTM was used, to extract temporal information from all successive image frames to predict the final surgical phase. The proposed method was evaluated with a public dataset Cholec80. The proposed approach outperformed state-of-the-art methods, showing a high F1-score of 87.12% and an AUC of 98.00%. In addition, the F1-score deviation between all phases decreased by about 10% compared to that before applying undersampling. Experimental results confirmed that employing our proposed method could learn enrich temporal information from short clips. It outperformed the conventional one-stream CNN-LSTM architecture.

Multi-task learning for X-vector based speaker recognition

In this paper, we propose a speaker recognition system that leverages multi-task learning and features integration (MTFI), to improve the performance of x-vector based speaker recognition models. It is important to integrate complementary information from different features such as MFCC, Fbank, spectrogram and LPCC, as often a single feature usually cannot cover all information about a speaker and generalization is insufficient. Since the x-vector model outputs affine transformation values with the penultimate hidden layer in the trained model, the parameter distribution of this layer should be stable and should not be affected by tasks that are not current branches when switching tasks. Therefore, we propose a shared unit (SU) in multi-task learning, which is useful for sharing common representations and other auxiliary tasks. Then, an attention mechanism is designed to calculate the frame weight in the statistical pooling layer, so as to enhance the key frame information. The proposed system had an EER of 0.98% in voxceleb1 and the average score fusion obtained the EER of 0.65%.

Fact or fiction: An experiment on how information sources and message framing influence vaccine risk perception

In view of the growing disinformation about vaccines on social media since the beginning of the Covid-19 pandemic, effective communication strategies encouraging vaccine uptake are needed. We conducted an experiment through an online, preregistered survey to explore which types of information sources are more trusted by the population regarding the risks of the Covid-19 booster, and which types of message frames are more effective in influencing the perception of risks for children. We surveyed a representative sample composed of 1,800 Spaniards in June 2022. The two dependent variables were respondents’ perceptions of (1) the Covid-19 booster vaccine effectiveness and (2) the safety of the Covid-19 vaccine for children. Participants were randomly exposed to different messaging regarding these vaccines, with different sources of information (scientific consensus, scientific dissensus, governmental, influencers and medical doctors), and different message framing (pro- and anti-vaccine storytelling and pro- and anti-vaccine scientific data). Additionally, some respondents who did not receive any messaging formed a control group. Our findings suggest that different information sources and frames can influence people’s risk perception of vaccines. The source ‘medical doctors’ had a positive effect on risk perception of the Covid-19 booster vaccine (p < 0.05), and pro-vaccine messages, in the form of both storytelling and scientific expository frames, had a positive effect on respondents’ risk perception of the vaccine for children (p < 0.1 and p < 0.05, respectively). On the one hand, male and older respondents rated booster vaccines as more effective than female and younger respondents. On the other hand, right-wing respondents believed vaccines are somewhat less safe for children than left-wing respondents. These findings might support the development of strategic communication in vaccination programmes by public health departments to improve immunization rates in the general population. The practical and theoretical implications are discussed.

How Do Physicians Frame Medical Information in Talks With Their Patients? An Inductive Microanalysis.

During medical consultations, physicians need to share a substantial amount of information with their patients. How this information is framed can be crucial for patient understanding and outcomes, but little is known about the details of how physicians frame information in practice. Using an inductive microanalysis approach in the study of videotaped medical interactions, we aimed to identify the information frames (i.e., higher-level ways of organizing and structuring information to reach a particular purpose) and the information-framing devices (i.e., any dialogic mechanism used to present information in a particular way that shapes how the patient might perceive and interpret it) physicians use spontaneously and intuitively while sharing information with their patients. We identified 66 different information-framing devices acting within nine information frames conveying: (1) Do we agree that we share this knowledge?, (2) I don't like where I (or where you are) am going with this, (3) This may be tricky to understand, (4) You may need to think, (5) This is important, (6) This is not important, (7) This comes from me as a doctor, (8) This comes from me as a person, and (9) This is directed to you as a unique person. The kaleidoscope of information-framing devices described in this study reveals the near impossibility for neutrality and objectivity in the information-sharing practice of medical care. It also represents an inductively derived starting point for further research into aspects of physicians' information-sharing praxis.

A Lightweight Recurrent Grouping Attention Network for Video Super-Resolution.

Effective aggregation of temporal information of consecutive frames is the core of achieving video super-resolution. Many scholars have utilized structures such as sliding windows and recurrences to gather the spatio-temporal information of frames. However, although the performances of constructed video super-resolution models are improving, the sizes of the models are also increasing, exacerbating the demand on the equipment. Thus, to reduce the stress on the device, we propose a novel lightweight recurrent grouping attention network. The parameters of this model are only 0.878 M, which is much lower than the current mainstream model for studying video super-resolution. We have designed a forward feature extraction module and a backward feature extraction module to collect temporal information between consecutive frames from two directions. Moreover, a new grouping mechanism is proposed to efficiently collect spatio-temporal information of the reference frame and its neighboring frames. The attention supplementation module is presented to further enhance the information gathering range of the model. The feature reconstruction module aims to aggregate information from different directions to reconstruct high-resolution features. Experiments demonstrate that our model achieves state-of-the-art performance on multiple datasets.

Multiview feature co‐factorization based dictionary selection for video summarization

AbstractRecently, video summarization (VS) has emerged as one of the most effective tools for rapidly understanding video big data. Dictionary selection based on self‐representation and sparse regularization is consistent with the requirement of VS, which aims to represent the original video with little reconstruction error by a small number of video frames. However, one crucial issue is that the existing methods mainly use a single view feature, which is not sufficient enough for acquiring the full pictorial details and affects the quality of the produced video summary. Although a few methods use more than one features, they only directly concatenate the features, which does not take advantage of the relationship of different features. Considering the complementarity of shallow and deep features, multiview feature co‐factorization based dictionary selection for VS is proposed in this paper to use the common information of both view features for VS. Specifically, two view features are used to fully exploit the full pictorial information of video frames, then the common information of two different views is extracted through coupled matrix factorization to conduct the dictionary selection for VS. Experiments have been carried out on two benchmark datasets, and results have demonstrated the effectiveness and superiority of the proposed method.

Does the Framing of Information Regarding Foreign Election Interference Matter? Evidence from a Survey Experiment in Canada

Does the Framing of Information Regarding Foreign Election Interference Matter? Evidence from a Survey Experiment in Canada

Strategi Pengelolaan Kelas Dalam Menciptakan Suasana Belajar Untuk Meningkatkan Efektivitas Pembelajaran Sejarah Kelas X Melalui Penggunaan Aplikasi Quiziz di SMA Negeri 1 Pahunga Lodu

This study aims to find out how to increase the effectiveness of history learning through the use of the Quiziz application on a Quiziz learning media. This research is a class activity research that will be carried out on class X students at SMA Negeri 1 Pahunga Lodu with a sample of 34 students. This research was carried out when the learning process in the classroom was started or it could also be used as homework. Each meeting consists of 3 stages, namely, planning stage, implementation stage, and observation. This research uses quantitative methods, quantitative research is carried out by collecting information in a number frame, then it is prepared and analyzed to obtain data. In this study, using ex-post facto to design and explain the causal relationship. In this case, it will explore causal relationships and test hypotheses between variables that have been formulated previously. The variable is the use of the Quiziz application learning media in increasing the effectiveness of learning in the History subject of Class X students at SMA Negeri 1 Pahunga Lodu. Based on the results of the analysis on the variables using the quiziz application, the students of class X IPS 4 SMA Negeri 1 Pahunga Lodu can be seen that the score that has been obtained by students is 100, and the minimum score obtained by students is 50. The average score obtained is 50. Students have obtained the variable (X) 87,26472 with a range of 50. While the values for skewnes and kurtosis are -1.7047 and 2.812362, respectively, and a standard deviation of 12.46889 from the ideal score that may be achieved by students. While the results of the output on the Normality test, it can be seen that the significant value (Y) is 0.013 0.05, so H1 received is normally distributed. Thus it can be concluded that in learning activities using the internet-based Quiziz application learning model or method has a positive effect on student learning achievement.

Decoding the animated text-based captchas to verify their robustness against automated attacks

In order to protect the web against automated attacks, CAPTCHAs are most widely used mechanism on the internet. Numerous types of CAPTCHAs are introduced due to weaknesses in the earlier designs. Animated CAPTCHAs are one of the design alternatives. Instead of presenting the whole information at once, animated CAPTCHAs present information in various frames over the specific interval of time. As CATPCHAs are ubiquitously used to avoid the serious threats from bots therefore it is important to verify their effectiveness. In this research we have verified their robustness against machine learning attacks. It has been proved that adding the extra time dimension does not necessarily ensure protection against automated attacks. We have attacked the Hello CAPTCHA scheme, which is the most popular animated CAPTCHA scheme available on the internet. By applying novel image processing and machine learning techniques, these CAPTCHAs are decoded with high precision. A pre-trained CNN is used to recognize the extracted characters. In this research, 6 popular types of animated CAPTCHAs along with 41 sub types were successfully deciphered with an overall precision of up to 99.5 %.

MPAF-CNN: Multiperspective aware and fine-grained fusion strategy for speech emotion recognition

Speech emotion recognition (SER) is a crucial and challenging task in affective computing due to the intricacy and variability inherent in speech. In this paper, a novel method (i.e., MPAF-CNN) combines a convolutional neural network (CNN)-based multiperspective aware module (MPAM) and a frame-level fine-grained fusion strategy (FFS) for SER by utilizing speech information. MPAM perceives the emotional information embedded in speech from three main perspectives: local, frame-level, and global. Specifically, this module introduces the multiscale idea of perceiving multi-granular emotional information under different local sensory fields from the local perspective; a novel frame-level aggregated attention is proposed in this paper, aiming to learn the intrinsic emotional associations of intermediate features from the frame-level perspective, enhance the model's attention to emotionally informative frames, and improve the emotional expression of intermediate features; in the global perspective, multiple layers of global intermediate features are aggregated from the time domain, frequency domain, or channel to enhance the model's ability to extract and express global feature information. A new frame-level fine-grained fusion strategy is proposed to employ an attention mechanism to model the interaction of emotional representations from different acoustic features at the frame level, capturing their underlying relationships and thus further improving the overall performance of the model. The experimental results show that our method has excellent performance in recognizing speech emotions, and MPAF-CNN obtains 72.19% and 72.88% recognition accuracy on the IEMOCAP database.

A References Architecture for Human Cyber Physical Systems - PART II: Fundamental Design Principles for Human-CPS Interaction

As automation increases qualitatively and quantitatively in safety-critical human cyber-physical systems, it is becoming more and more challenging to increase the probability or ensure that human operators still perceive key artefacts and comprehend their roles in the system. In the companion paper, we proposed an abstract reference architecture capable of expressing all classes of system-level interactions in human cyber-physical systems. Here we demonstrate how this reference architecture supports the analysis of levels of communication between agents and helps to identify the potential for misunderstandings and misconceptions. We then develop a metamodel for safe human machine interaction. Therefore, we ask what type of information exchange must be supported on what level so that humans and systems can cooperate as a team, what is the criticality of exchanged information, what are timing requirements for such interactions, and how can we communicate highly critical information in a limited time frame in spite of the many sources of a distorted perception. We highlight shared stumbling blocks and illustrate shared design principles, which rest on established ontologies specific to particular application classes. In order to overcome the partial opacity of internal states of agents, we anticipate a key role of virtual twins of both human and technical cooperation partners for designing a suitable communication.

Continuous sign language recognition based on hierarchical memory sequence network

AbstractWith the goal of solving the problem of feature extractors lacking strong supervision training and insufficient time information concerning single‐sequence model learning, a hierarchical sequence memory network with a multi‐level iterative optimisation strategy is proposed for continuous sign language recognition. This method uses the spatial‐temporal fusion convolution network (STFC‐Net) to extract the spatial‐temporal information of RGB and Optical flow video frames to obtain the multi‐modal visual features of a sign language video. Then, in order to enhance the temporal relationships of visual feature maps, the hierarchical memory sequence network is used to capture local utterance features and global context dependencies across time dimensions to obtain sequence features. Finally, the decoder decodes the final sentence sequence. In order to enhance the feature extractor, the authors adopted a multi‐level iterative optimisation strategy to fine‐tune STFC‐Net and the utterance feature extractor. The experimental results on the RWTH‐Phoenix‐Weather multi‐signer 2014 dataset and the Chinese sign language dataset show the effectiveness and superiority of this method.

Endoscopic image classification algorithm based on Poolformer.

Image desmoking is a significant aspect of endoscopic image processing, effectively mitigating visual field obstructions without the need for additional surgical interventions. However, current smoke removal techniques tend to apply comprehensive video enhancement to all frames, encompassing both smoke-free and smoke-affected images, which not only escalates computational costs but also introduces potential noise during the enhancement of smoke-free images. In response to this challenge, this paper introduces an approach for classifying images that contain surgical smoke within endoscopic scenes. This classification method provides crucial target frame information for enhancing surgical smoke removal, improving the scientific robustness, and enhancing the real-time processing capabilities of image-based smoke removal method. The proposed endoscopic smoke image classification algorithm based on the improved Poolformer model, augments the model's capacity for endoscopic image feature extraction. This enhancement is achieved by transforming the Token Mixer within the encoder into a multi-branch structure akin to ConvNeXt, a pure convolutional neural network. Moreover, the conversion to a single-path topology during the prediction phase elevates processing speed. Experiments use the endoscopic dataset sourced from the Hamlyn Centre Laparoscopic/Endoscopic Video Dataset, augmented by Blender software rendering. The dataset comprises 3,800 training images and 1,200 test images, distributed in a 4:1 ratio of smoke-free to smoke-containing images. The outcomes affirm the superior performance of this paper's approach across multiple parameters. Comparative assessments against existing models, such as mobilenet_v3, efficientnet_b7, and ViT-B/16, substantiate that the proposed method excels in accuracy, sensitivity, and inference speed. Notably, when contrasted with the Poolformer_s12 network, the proposed method achieves a 2.3% enhancement in accuracy, an 8.2% boost in sensitivity, while incurring a mere 6.4 frames per second reduction in processing speed, maintaining 87 frames per second. The results authenticate the improved performance of the refined Poolformer model in endoscopic smoke image classification tasks. This advancement presents a lightweight yet effective solution for the automatic detection of smoke-containing images in endoscopy. This approach strikes a balance between the accuracy and real-time processing requirements of endoscopic image analysis, offering valuable insights for targeted desmoking process.

Statistically unbiased prediction enables accurate denoising of voltage imaging data

Here we report SUPPORT (statistically unbiased prediction utilizing spatiotemporal information in imaging data), a self-supervised learning method for removing Poisson–Gaussian noise in voltage imaging data. SUPPORT is based on the insight that a pixel value in voltage imaging data is highly dependent on its spatiotemporal neighboring pixels, even when its temporally adjacent frames alone do not provide useful information for statistical prediction. Such dependency is captured and used by a convolutional neural network with a spatiotemporal blind spot to accurately denoise voltage imaging data in which the existence of the action potential in a time frame cannot be inferred by the information in other frames. Through simulations and experiments, we show that SUPPORT enables precise denoising of voltage imaging data and other types of microscopy image while preserving the underlying dynamics within the scene.

Framing of Information, Psychological Distance, and Belief in Health Related Information under Time Pressure in Older Adults

The time of pandemics could be described by the overflow of health related news in media, but also the rise of researches concerning it. However, there is still a lack of information about message characteristics which effect belief in it, besides older people are underrepresented in these studies. Belief in fake news is especially dangerous for older people, not only because fake news usually promotes dangerous behavior (e.g. do not seek COVID-19 vaccination), but also because older people are the ones who are most likely to share fake news on social media in such way helping to spread them. The aim of the study was to estimate the influence of information framing and psychological distance on belief in health related information under time pressure in older adults. Study was based on representable sample of 50 years and older Lithuanians. In total 505 participants took part in the study. 200 (30,6 %) were men, 305 (60,4%) were women. Participants ranged in age from 50 to 94 with the mean age of 66,27 (SD = 11,24). Study was a between-subject design experiment. Belief in Health related news information served as a dependent variable, Framing of Information and Psychological Distance as independent variables, also age, gender and education were control variables. Participants were presented with eight fake and eight true news headlines about vaccination and COVID-19 in the form of social media posts for 7 seconds and had to evaluate their belief in these headlines. Results indicate, that neither psychological distance, nor information framing have any influence on overall belief in health related information in older adults. Even though gender and education were not related to overall belief in news, a significant positive correlation between age and belief in health related information was found. Our research prove that older people become more truth biased with age.

Detecting Deepfake Videos Using Spatiotemporal Trident Network

The widespread dissemination of Deepfake in social networks has posed serious security risks, thus necessitating the development of an effective Deepfake detection technique. Currently, video-based detectors have not been explored as extensively as image-based detectors. Most existing video-based methods only consider temporal features without combining spatial features, and do not mine deeper-level subtle forgeries, resulting in limited detection performance. In this paper, a novel spatiotemporal trident network (STN) is proposed to detect both spatial and temporal inconsistencies of Deepfake videos. Since the large amount of redundant information in Deepfake video frames, we introduce convolutional block attention module (CBAM) on the basis of the I3D network and optimize the structure to make the network better focus on the meaningful information of the input video. Aiming at the defects in the deeper-level subtle forgeries, we designed three feature extraction modules (FEMs) of RGB, optical flow, and noise to further extract deeper video frame information. Extensive experiments on several well-known datasets demonstrate that our method has promising performance, surpassing several state-of-the-art Deepfake video detection methods.

A deep learning pipeline for automated classification of vocal fold polyps in flexible laryngoscopy.

To develop and validate a deep learning model for distinguishing healthy vocal folds (HVF) and vocal fold polyps (VFP) on laryngoscopy videos, while demonstrating the ability of a previously developed informative frame classifier in facilitating deep learning development. Following retrospective extraction of image frames from 52 HVF and 77 unilateral VFP videos, two researchers manually labeled each frame as informative or uninformative. A previously developed informative frame classifier was used to extract informative frames from the same video set. Both sets of videos were independently divided into training (60%), validation (20%), and test (20%) by patient. Machine-labeled frames were independently verified by two researchers to assess the precision of the informative frame classifier. Two models, pre-trained on ResNet18, were trained to classify frames as containing HVF or VFP. The accuracy of the polyp classifier trained on machine-labeled frames was compared to that of the classifier trained on human-labeled frames. The performance was measured by accuracy and area under the receiver operating characteristic curve (AUROC). When evaluated on a hold-out test set, the polyp classifier trained on machine-labeled frames achieved an accuracy of 85% and AUROC of 0.84, whereas the classifier trained on human-labeled frames achieved an accuracy of 69% and AUROC of 0.66. An accurate deep learning classifier for vocal fold polyp identification was developed and validated with the assistance of a peer-reviewed informative frame classifier for dataset assembly. The classifier trained on machine-labeled frames demonstrates improved performance compared to the classifier trained on human-labeled frames.

ANALISIS FRAMING TENTANG PEMBERITAAN PEMINDAHAN IBU KOTA NEGARA PADA MEDIA ONLINE REPUBLIKA.CO.ID DAN KOMPAS.COM

Discussions on moving the State Capital (IKN) in early 2019 became one of the hot topics in the country and media attention in Indonesia. Framing is the framing of information used by a media. The selection of the news portals Republika.co.id and Kompas.com is not without reason. kompas.com occupies the 9th position and Republika.co.id occupies the 34th position, included in the category of the top 50 sites in Indonesia. This research intends to identify the framing of national mass media coverage of the decision to move the State Capital (IKN) to Kalimantan. This research is a type of qualitative descriptive research, using the Zhongdang Pan and Gerald M. Kosicki framing analysis model which has four analytical tools, namely syntax, script, thematic, and rhetorical. Data collection techniques in this research use techniques through primary data and secondary data. This research was conducted through observing online news texts on the media Republika.co.id and kompas.com by selecting 5 stories in each media for the period March to April 2022. Based on the data that has been found from 5 news stories in both media, there are each one news that does not meet the elements of completeness of the news. The comparison of framing in the information that sticks out by Republika.co.id and kompas.com is most often seen in the way the facts are presented and the selection of sources. The results of this study show that Republika.co.id constructs more of a government figure in following up on issues in the process of transferring IKN.

Learning facial expression and body gesture visual information for video emotion recognition

Recent research has shown that facial expressions and body gestures are two significant implications in identifying human emotions. However, these studies mainly focus on contextual information of adjacent frames, and rarely explore the spatio-temporal relationships between distant or global frames. In this paper, we revisit the facial expression and body gesture emotion recognition problems, and propose to improve the performance of video emotion recognition by extracting the spatio-temporal features via further encoding temporal information. Specifically, for facial expression, we propose a super image-based spatio-temporal convolutional model (SISTCM) and a two-stream LSTM model to capture the local spatio-temporal features and learn global temporal cues of emotion changes. For body gestures, a novel representation method and an attention-based channel-wise convolutional model (ACCM) are introduced to learn key joints features and independent characteristics of each joint. Extensive experiments on five common datasets are carried out to prove the superiority of the proposed method, and the results proved learning two visual information leads to significant improvement over the existing state-of-the-art methods.