Mental health issues and needs have increased substantially since the onset of the COVID-19 pandemic. However, health policy and decision-makers do not have adequate data and tools to predict population-level mental health demand, especially amid a crisis. This study investigates whether situational indicators and social media emotions can be effectively used to predict public mental health needs. We collected time-series data from multiple sources in Singapore between 1 July 2020 and 31 December 2021, including daily-level records of situation indicators, emotions expressed on social media, and mental health needs measured by the number of public visits to the emergency room of the country's largest psychiatric hospital, and use of government-initiated online mental health self-help portal. Compared to mental health needs data alone, social media emotions were found to have significant Granger-causality effects with as early as four to five days lag length. Each resulted in a statistically significant enhancement in predicting the public's visits to the emergency room and the online self-help portal (e.g., Facebook Anger Count on emergency room visits, χ2 = 13·7, P = ·0085**). In contrast, situational indicators such as daily new cases had Granger-causality effects (χ2 = 10·3, P = ·016*) with a moderate lag length of three days. The findings indicate that emotions algorithmically extracted from social media platforms can provide new indicators for tracking and forecasting population-level mental health states and needs.

The COVID-19 pandemic has claimed millions of lives worldwide and elicited heightened emotions. This study examines the expression of various emotions pertaining to COVID-19 in the United States and India as manifested in over 54 million tweets, covering the fifteen-month period from February 2020 through April 2021, a period which includes the beginnings of the huge and disastrous increase in COVID-19 cases that started to ravage India in March 2021. Employing pre-trained emotion analysis and topic modeling algorithms, four distinct types of emotions (fear, anger, happiness, and sadness) and their time- and location-associated variations were examined. Results revealed significant country differences and temporal changes in the relative proportions of fear, anger, and happiness, with fear declining and anger and happiness fluctuating in 2020 until new situations over the first four months of 2021 reversed the trends. Detected differences are discussed briefly in terms of the latent topics revealed and through the lens of appraisal theories of emotions, and the implications of the findings are discussed.

Emotional expressions form a key part of user behavior on today's digital platforms. While multimodal emotion recognition techniques are gaining research attention, there is a lack of deeper understanding on how visual and non-visual features can be used to better recognize emotions in certain contexts, but not others. This study analyzes the interplay between the effects of multimodal emotion features derived from facial expressions, tone and text in conjunction with two key contextual factors: i) gender of the speaker, and ii) duration of the emotional episode. Using a large public dataset of 2,176 manually annotated YouTube videos, we found that while multimodal features consistently outperformed bimodal and unimodal features, their performance varied significantly across different emotions, gender and duration contexts. Multimodal features performed particularly better for male speakers in recognizing most emotions. Furthermore, multimodal features performed particularly better for shorter than for longer videos in recognizing neutral and happiness, but not sadness and anger. These findings offer new insights towards the development of more context-aware emotion recognition and empathetic systems.

Background Public sentiments are an important indicator of crisis response, with the need to balance exigency without adding to panic or projecting overconfidence. Given the rapid spread of the COVID-19 pandemic, governments have enacted various nationwide measures against the disease with social media platforms providing the previously unparalleled communication space for the global populations. Objective This research aims to examine and provide a macro-level narrative of the evolution of public sentiments on social media at national levels, by comparing Twitter data from India, Singapore, South Korea, the United Kingdom, and the United States during the current pandemic. Methods A total of 67,363,091 Twitter posts on COVID-19 from January 28, 2020, to April 28, 2021, were analyzed from the 5 countries with “wuhan,” “corona,” “nCov,” and “covid” as search keywords. Change in sentiments (“very negative,” “negative,” “neutral or mixed,” “positive,” “very positive”) were compared between countries in connection with disease milestones and public health directives. Results Country-specific assessments show that negative sentiments were predominant across all 5 countries during the initial period of the global pandemic. However, positive sentiments encompassing hope, resilience, and support arose at differing intensities across the 5 countries, particularly in Asian countries. In the next stage of the pandemic, India, Singapore, and South Korea faced escalating waves of COVID-19 cases, resulting in negative sentiments, but positive sentiments appeared simultaneously. In contrast, although negative sentiments in the United Kingdom and the United States increased substantially after the declaration of a national public emergency, strong parallel positive sentiments were slow to surface. Conclusions Our findings on sentiments across countries facing similar outbreak concerns suggest potential associations between government response actions both in terms of policy and communications, and public sentiment trends. Overall, a more concerted approach to government crisis communication appears to be associated with more stable and less volatile public sentiments over the evolution of the COVID-19 pandemic.

Background With the World Health Organization’s pandemic declaration and government-initiated actions against coronavirus disease (COVID-19), sentiments surrounding COVID-19 have evolved rapidly. Objective This study aimed to examine worldwide trends of four emotions—fear, anger, sadness, and joy—and the narratives underlying those emotions during the COVID-19 pandemic. Methods Over 20 million social media twitter posts made during the early phases of the COVID-19 outbreak from January 28 to April 9, 2020, were collected using “wuhan,” “corona,” “nCov,” and “covid” as search keywords. Results Public emotions shifted strongly from fear to anger over the course of the pandemic, while sadness and joy also surfaced. Findings from word clouds suggest that fears around shortages of COVID-19 tests and medical supplies became increasingly widespread discussion points. Anger shifted from xenophobia at the beginning of the pandemic to discourse around the stay-at-home notices. Sadness was highlighted by the topics of losing friends and family members, while topics related to joy included words of gratitude and good health. Conclusions Overall, global COVID-19 sentiments have shown rapid evolutions within just the span of a few weeks. Findings suggest that emotion-driven collective issues around shared public distress experiences of the COVID-19 pandemic are developing and include large-scale social isolation and the loss of human lives. The steady rise of societal concerns indicated by negative emotions needs to be monitored and controlled by complementing regular crisis communication with strategic public health communication that aims to balance public psychological wellbeing.

This paper describes a system developed for detecting propaganda techniques from news articles. We focus on examining how emotional salience features extracted from a news segment can help to characterize and predict the presence of propaganda techniques. Correlation analyses surfaced interesting patterns that, for instance, the "loaded language" and "slogan" techniques are negatively associated with valence and joy intensity but are positively associated with anger, fear and sadness intensity. In contrast, "flag waving" and "appeal to fear-prejudice" have the exact opposite pattern. Through predictive experiments, results further indicate that whereas BERT-only features obtained F1-score of 0.548, emotion intensity features and BERT hybrid features were able to obtain F1-score of 0.570, when a simple feedforward network was used as the classifier in both settings. On gold test data, our system obtained micro-averaged F1-score of 0.558 on overall detection efficacy over fourteen propaganda techniques. It performed relatively well in detecting "loaded language" (F1 = 0.772), "name calling and labeling" (F1 = 0.673), "doubt" (F1 = 0.604) and "flag waving" (F1 = 0.543).

Water quality assessment has always been of primary importance before consumption as most of the available water is polluted, which could transmit several waterborne diseases. Water Quality Index (WQI) is a unique single value to determine overall water quality. WQI summarizes the water quality parameters in a single value. MATLAB fuzzy is the standard toolbox to implement the water quality index. The user has to determine only the inputs as different water quality parameters and the membership functions based on the complexity of the application. This approach is offline, as it cannot be implemented in real-time. An alternate method may be the WQI measurement in the Python framework for real-time implementation. In this paper, we are trying to find out that it is possible to switch from MATLAB fuzzy toolbox to the Python framework for real-time implementation. The WQI measurement is performed in both the fuzzy toolbox from MATLAB® and Python 3.4. Based on the results, a comparative study has been done, and the switching possibility is found out.

Emotional expressions form a key part of user behavior on today's digital platforms. While multimodal emotion recognition techniques are gaining research attention, there is a lack of deeper understanding on how visual and non-visual features can be used in better recognizing emotions for certain contexts, but not others. This study analyzes the interplay between the effects of multimodal emotion features derived from facial expressions, tone and text in conjunction with two key contextual factors: 1) the gender of the speaker, and 2) the duration of the emotional episode. Using a large dataset of more than 2500 manually annotated videos from YouTube, we found that while multimodal features consistently outperformed bimodal and unimodal features, their performances varied significantly for different emotions, gender and duration contexts. Multimodal features were found to perform particularly better for male than female speakers in recognizing most emotions except for fear. Furthermore, multimodal features performed particularly better for shorter than for longer videos in recognizing neutral, happiness, and surprise, but not sadness, anger, disgust and fear. These findings offer new insights towards the development of more context-aware emotion recognition and empathetic systems.

This paper describes a large global dataset on people's discourse and responses to the COVID-19 pandemic over the Twitter platform. From 28 January 2020 to 1 June 2022, we collected and processed over 252 million Twitter posts from more than 29 million unique users using four keywords: "corona", "wuhan", "nCov" and "covid". Leveraging probabilistic topic modelling and pre-trained machine learning-based emotion recognition algorithms, we labelled each tweet with seventeen attributes, including a) ten binary attributes indicating the tweet's relevance (1) or irrelevance (0) to the top ten detected topics, b) five quantitative emotion attributes indicating the degree of intensity of the valence or sentiment (from 0: extremely negative to 1: extremely positive) and the degree of intensity of fear, anger, sadness and happiness emotions (from 0: not at all to 1: extremely intense), and c) two categorical attributes indicating the sentiment (very negative, negative, neutral or mixed, positive, very positive) and the dominant emotion (fear, anger, sadness, happiness, no specific emotion) the tweet is mainly expressing. We discuss the technical validity and report the descriptive statistics of these attributes, their temporal distribution, and geographic representation. The paper concludes with a discussion of the dataset's usage in communication, psychology, public health, economics, and epidemiology.

This paper explores the use of emotion intensity analysis in predicting and understanding the ingredients of happiness as expressed in text. We show that by using just the five dimensions of emotion intensity features (i.e., joy, anger, fear, sadness and overall valence), we can achieve good accuracies in classifying agency (i.e., whether or not the author of the happy moment is in control) (ACC=73.8%, AUC=.579, F1=.849) and in classifying social (i.e., whether or not the happy moment involves other people) (ACC=60.3%, AUC=.637, F1=.603). By integrating emotion intensity with sentiment, linguistics, demographics, concepts, and word embedding features, our final hybrid model performed significantly better for agency (ACC=83.5%, AUC=.887, F1=.893) and for social (ACC=90.3%, AUC=.959, F1=.907) predictions. Furthermore, we uncovered interesting patterns in how emotion intensities characterized happiness expressions across the various concepts (e.g., family, food, career, animals), between the two reflection periods (24 hours vs. 3 months), and across seven user-generated content corpora sources (HappyDB vs. MySpace, Runners World, Twitter, Digg, BBC and YouTube).

This paper studies the properties of socially popular news with a focused interest on the emotions conveyed through their headlines. We delve deeply into the notion of emotional salience in news values and extract the emotion intensities features across the valence, joy, anger, fear and sadness dimensions. A novel dataset consisting of 47,611 English news headlines from six publishers that received more than 17 million shares and likes were retrieved using Facebook APIs over ten consecutive months in 2018. In contrast with the conventional knowledge that only high-arousal, negative emotions are associated with viral news, the data revealed that headlines with higher intensities across all five emotion dimensions (including positive, joyful news) are significantly associated with social popularity, though the emotion-popularity correlation patterns differ for different publishers (e.g., daily broadcast vs. politics-slanted publishers). From the predictive experiments, we found that the emotion features had complimentary benefits to existing features, which included strong baselines features and word embedding. The final hybrid model achieved the highest predictive performance (R^2 = .54, tau = .53; F1 = .44, AUC = .85). Using two additional publishers' data, robustness tests further showed the advantage of the proposed model against a state-of-the-art method: The Guardian (tau = .45 vs. .37) and The New York Times (tau = .46 vs. .32).

While sentiment and emotion analysis has received a considerable amount of research attention, the notion of understanding and detecting the intensity of emotions is relatively less explored. This paper describes a system developed for predicting emotion intensity in tweets. Given a Twitter message, CrystalFeel uses features derived from parts-of-speech, n-grams, word embedding, and multiple affective lexicons including Opinion Lexicon, SentiStrength, AFFIN, NRC Emotion & Hash Emotion, and our in-house developed EI Lexicons to predict the degree of the intensity associated with fear, anger, sadness, and joy in the tweet. We found that including the affective lexicons-based features allowed the system to obtain strong prediction performance, while revealing interesting emotion word-level and message-level associations. On gold test data, CrystalFeel obtained Pearson correlations of 0.717 on average emotion intensity and of 0.816 on sentiment intensity.

This paper describes a system developed for a shared sentiment analysis task and its subtasks organized by SemEval-2017. A key feature of our system is the embedded ability to detect sarcasm in order to enhance the performance of sentiment classification. We first constructed an affect-cognition-sociolinguistics sarcasm features model and trained a SVM-based classifier for detecting sarcastic expressions from general tweets. For sentiment prediction, we developed CrystalNest– a two-level cascade classification system using features combining sarcasm score derived from our sarcasm classifier, sentiment scores from Alchemy, NRC lexicon, n-grams, word embedding vectors, and part-of-speech features. We found that the sarcasm detection derived features consistently benefited key sentiment analysis evaluation metrics, in different degrees, across four subtasks A-D.

In this paper, we present a color transfer algorithm to colorize a broad range of gray images without any user intervention. The algorithm uses a machine learning-based approach to automatically colorize grayscale images. The algorithm uses the superpixel representation of the reference color images to learn the relationship between different image features and their corresponding color values. We use this learned information to predict the color value of each grayscale image superpixel. As compared to processing individual image pixels, our use of superpixels helps us to achieve a much higher degree of spatial consistency as well as speeds up the colorization process. The predicted color values of the gray-scale image superpixels are used to provide a 'micro-scribble' at the centroid of the superpixels. These color scribbles are refined by using a voting based approach. To generate the final colorization result, we use an optimization-based approach to smoothly spread the color scribble across all pixels within a superpixel. Experimental results on a broad range of images and the comparison with existing state-of-the-art colorization methods demonstrate the greater effectiveness of the proposed algorithm.

The Internet has a huge volume of unlabeled videos from diverse sources, making it difficult for video providers to organize and for viewers to consume the content. This paper defines the problem of video aboutness generation (i.e., the automatic generation of a concise natural-language description about a video) and characterizes its differences from closely related problems such as video summarization and video caption. We then made an attempt to provide a solution to this problem. Our proposed system exploits multi-modal analyses of audio, text and visual content of the video and leverages the Internet to identify a top-matched aboutness description. Through an exploratory study involving human judges evaluating a variety of test videos, we found support of the proposed approach.

Mid-level image features have been shown to be helpful to bridge the semantic gap between low-level and high-level image representations. Many existing methods to learn mid-level visual elements consider each mid-level feature individually, and do not take their mutual relationships into account. We follow the intuitive idea that learning discriminative combinations of visual elements can help us deal with ambiguities better, and propose the concept of visual n-grams to effectively represent combinations of visual elements along with their relative spatial configuration and co-occurrence relationships. An overview of our approach is shown in Figure 1. Figure 1 (a) shows the process of learning discriminative visual n-grams based on relative spatial position, orientation and co-occurrence relationships of mid-level image patches. Figure 1 (b) further shows how these visual n-grams are used to finally learn a feature vector representing test and training images.

The human population is increasing at an alarming rate, whereas heavy metals (HMs) pollution is mounting serious environmental problem, which could lead to serious concern about the future sufficiency of global food production. Some HMs such as Mn, Cu, and Fe, at lower concentration serves as an essential vital component of plant cell as they are crucial in various enzyme catalyzed biochemical reactions. At higher concentration, a vast variety of HMs such as Mn, Cu, Cd, Fe, Hg, Al and As, impose toxic reaction in the plant system which greatly affect the crop yield. Recently, microRNAs (miRNAs) that are small class of non-coding riboregulator have emerged as central regulator of numerous abiotic stresses including HMs. Increasing reports indicate that plants have evolved specialized inbuilt mechanism viz. signal transduction, translocation and sequestration to counteract the toxic response of HMs. Combining computational and wet laboratory approaches have produced sufficient evidences concerning active involvement of miRNAs during HMs toxicity response by regulating various transcription factors and protein coding genes involved in plant growth and development. However, the direct role of miRNA in controlling various signaling molecules, transporters and chelating agents of HM metabolism is poorly understood. This review focuses on the latest progress made in the area of direct involvement of miRNAs in signaling, translocation and sequestration as well as recently added miRNAs in response to different HMs in plants.

In this study, the authors present a new area‐based stereo matching algorithm that computes dense disparity maps for a real‐time vision system. Although many stereo matching algorithms have been proposed in recent years, correlation‐based algorithms still have an edge because of speed and less memory requirements. The selection of appropriate shape and size of the matching window is a difficult problem for correlation‐based algorithms. In the proposed approach, two correlation windows are used to improve the performance of the algorithm while maintaining its real‐time suitability. The CPU implementation of the proposed algorithm computes more than 10 frame/s. Unlike other area‐based stereo matching algorithms, this method works very well at disparity boundaries as well as in low textured image areas and computes a dense and sharp disparity map. Evaluations on the benchmark Middlebury stereo datasets have been performed to demonstrate the qualitative and quantitative performance of the proposed algorithm.

We present a new method to classify human activities by leveraging on the cues available from depth images alone. Towards this end, we propose a descriptor which couples depth and spatial information of the segmented body to describe a human pose. Unique poses (i.e. codewords) are then identified by a spatial-based clustering step. Given a video sequence of depth images, we segment humans from the depth images and represent these segmented bodies as a sequence of codewords. We exploit unique poses of an activity and the temporal ordering of these poses to learn subsequences of codewords which are strongly discriminative for the activity. Each discriminative subsequence acts as a classifier and we learn a boosted ensemble of discriminative subsequences to assign a confidence score for the activity label of the test sequence. Unlike existing methods which demand accurate tracking of 3D joint locations or couple depth with color image information as recognition cues, our method requires only the segmentation masks from depth images to recognize an activity. Experimental results on the publicly available Human Activity Dataset (which comprises 12 challenging activities) demonstrate the validity of our method, where we attain a precision/recall of 78.1%/75.4% when the person was not seen before in the training set, and 94.6%/93.1% when the person was seen before.