Real-time Mood Research Articles

Implementation of MATLAB image processing and AI for real-time mood prediction

This study proposes an advanced real-time mood prediction system that utilizes Convolutional Neural Networks (CNNs) and webcam-based Region of Interest (ROI) extraction. By employing MATLAB and its Computer Vision Toolbox, the system detects and preprocesses facial regions from live webcam feeds to accurately predict an individual’s mood. The performance of this system is validated using a custom dataset, showcasing its potential for applications in human-computer interaction, psychological assessments, and real-time monitoring. This approach highlights a significant advancement in combining AI and image processing for real-time emotional analysis.

Ecological momentary assessment of sleep, pain, and opioid use among adolescents following surgery.

Opioids are effective for acute pain management following surgery among adolescents, yet are associated with significant negative consequences, including respiratory depression and opioid misuse. Sleep deficiency is common following surgery and extant research indicates strong cross-sectional associations between sleep deficiency and increased problematic opioid use. This study examined longitudinal associations between postsurgical sleep deficiency and opioid use among adolescents undergoing outpatient surgery. We also examined daily pain and mood as mechanisms linking previous night's sleep deficiency and next day prescription opioid use. This prospective, observational study enrolled 106 adolescents (11-19 years) who underwent orthopedic outpatient surgery and collected pre-surgery and longitudinal measurements. Participants were 52% female, African-American (7%), American Indian/Alaska Native (7%), Hispanic (9%), Native Hawaiian or Other Pacific Islander (4%), or white, non-Hispanic (66%). Using ecological momentary assessment methods, participants reported sleep, pain, and mood in real time over the first 14 days following surgery. Postsurgical opioid use was measured using an electronic medication cap monitoring device, eCAPTM. Associations between variables were measured using multilevel structural equation modeling. Using multi-level mediation models, pain, but not mood-mediated associations between postsurgical sleep deficiency (sleep quality, total sleep time, sleep onset latency, and wake after sleep onset) and opioid use, at both the within-person and between-person levels. Results highlight that greater previous night's sleep deficiency (both generally and greater than a person's mean level) was associated with higher next day pain (both generally and greater than a person's mean level), which, in turn, was associated with higher opioid use. Furthermore, between-person total effect models provide support for sleep deficiency predicting higher opioid use. Our findings should be considered preliminary yet underscore the need for a comprehensive and personalized approach to postsurgical pain management and opioid use, potentially implementing interventions targeting sleep quality and quantity to reduce pain and opioid use.

Directional associations among real-time activity, sleep, mood, and daytime symptoms in major depressive disorder using actigraphy and ecological momentary assessment

Previous research has suggested that individuals with major depressive disorder (MDD) experienced alterations in sleep and activity levels. However, the temporal associations among sleep, activity levels, mood, and daytime symptoms in MDD have not been fully investigated. The present study aimed to fill this gap by utilizing real-time data collected across time points and days. 75 individuals with MDD and 75 age- and gender-matched healthy controls were recruited. Ecological momentary assessments (EMA) were adopted to assess real-time mood status for 7 days, and actigraphy was employed to measure day-to-day sleep-activity patterns. Multilevel modeling analyses were performed. Results revealed a bidirectional association between mood/daytime symptoms and activity levels across EMA intervals. Increased activity levels were predictive of higher alert cognition and positive mood, while an increase in positive mood also predicted more increase in activity levels in depressed individuals. A bidirectional association between sleep and daytime symptoms was also found. Alert cognition was found to be predictive of better sleep in the subsequent night. Contrariwise, higher sleep efficiency predicted improved alert cognition and sleepiness/fatigue the next day. A unidirectional association between sleep and activity levels suggested that higher daytime activity levels predicted a larger increase in sleep efficiency among depressed individuals. This study indicated how mood, activity levels, and sleep were temporally and intricately linked to each other in depressed individuals using actigraphy and EMA. It could pave the way for novel and efficacious treatments for depression that target not just mood but sleep and activity levels.

ChatGPT У ПІДГОТОВЦІ ФІЛОЛОГІВ І ПЕРЕКЛАДАЧІВ. ВИКЛИКИ І ПЕРСПЕКТИВИ

The article deals with the challenges and perspectives of using artificial intelligence tools based on the large language models in the practice of training professionals in linguistic and translation fields of study at higher education institutions. Based on the analysis of scientific publications, the methodical principles of correct and academically integer application of the artificial intelligence tools in pedagogical and translation practice have been outlined. Founded on the example of ChatGTP, the concept of the principal compatibility of its use with the norms of academic integrity has been suggested – for the improvement of learning outcomes of students and for the forming of critical rational thinking and optimization of time and resources use as well. Based on the personal pedagogic experience of the authors in teaching non-related – informational technological and philological disciplines and on the empirical material of completed classes with the use of ChatGTP, the weak points of artificial intelligence systems in the training of philologists and translators, the risks of their uncritical use, restricted efficiency in forming of professional competencies and especially of common background knowledge has been analyzed. The conclusion has been made about the necessity of combination the use of artificial intelligence in the real time mood with the forming methods of elaborated creative teaching tasks that do not provoke the plagiarism and about the increase of the share of vivid communication in foreign languages in practice of teaching linguistic and translation disciplines to prevent the domination of the hybrid quasi-communication with the chat-bot. At the same time, the positive role of artificial intelligence in generation of the text information with the correct, academically integer reference to its source and in the practical written translation of the narrow-specialized terminologically intensive text by their careful reviewing has been stated.

Postpartum Mood Assessment and Intervention Using a Smartphone-Based Application [ID: 1376272

INTRODUCTION: Postpartum depression affects up to 15% of women after childbirth, and those with a history of depression are at higher risk. Depression symptoms may develop at any time postpartum, but the current postdelivery follow-up schedule typically accommodates only one examination in the immediate 6 weeks after birth. Gator MOMitor, a smartphone application, was developed to provide real-time assessment of postpartum mental health and to facilitate early intervention. METHODS: After obtaining signed consent, the study participants downloaded the Gator MOMitor application to their phones before hospital discharge after delivery. The app prompted participants to complete a mood assessment via the Edinburgh Postpartum Depression Scale (EPDS) sent through the app daily in the first 2 weeks and once per week in postpartum weeks 3 through 6. Assessments could be completed within a 1-hour window, after which they were flagged as incomplete. Participants received two reminders. A greater than or equal to 12 score on EPDS or three consecutive nonresponses triggered a phone call from a nurse for follow-up. RESULTS: Among 401 women enrolled, 1,599 mood assessments were completed. Seventy-six of these were positive screens triggering calls from the nurse, where the same participant could have multiple positive screens. Fifty-six participants with positive screens were successfully contacted by a nurse, 11 were referred for a wellness check, 5 were referred to a specialist, and 2 were admitted to the hospital for further evaluation. CONCLUSION: Smartphone applications such as Gator MOMitor are effective tools for real-time mood assessment, early symptom recognition, and intervention for postpartum women.

Music recommender system using facial feature recognition

Facial expressions convey a lot of information about the emotional state of a person and even a small change in it can help to detect changes in an individual's mood. Researchers have conducted numerous studies in the fields of machine learning and computer vision, training ML models to detect various human emotions or moods based on captured facial features. In this research, a system was proposed which is capable of identifying the user's emotions and moods and suggesting a list of appropriate songs to improve their mood. Incorporating mood detection offers significant benefits to customers' mental health and personal satisfaction. The objective of this system is to capture the user's image, detect their mood and create a music player system that recommends music based on the user's real-time mood, utilizing a web camera and deep learning algorithms.

Editorial: Politics is not a spectator sport: On the role of psycholinguists in a global crisis

Editorial: Politics is not a spectator sport: On the role of psycholinguists in a global crisis

User Engagement With Mood-Related Content on the National Cancer Institute Smokefree.Gov Initiative Cessation Resources.

This study aimed to examine engagement with mood-related content on the Smokefree.gov Initiative's smoking cessation resources. Smokefree.gov website analytics (July 2018-July 2019) were analyzed for user interactions with mood content on informational webpages and interactive self-assessment tools (mood quizzes, smoking quit plans). We also examined mood feature engagement (texting or pressing a command button for mood support) among text program and app users (July 2018-July 2019). Mood webpage views comprised 1.5% of all Smokefree.gov webpage views. Depression quizzes represented 82.9% of quiz completions, and stress quizzes represented 0.4% of quiz completions. Stress, anxiety, and low mood were the most reported smoking triggers on quit plans. Approximately 7,000 text program users and 3,000 app users sought real-time mood support. Given the importance of mood management in the smoking cessation process these findings demonstrate promising opportunities to increase the reach of mood support resources.

Geospatial Analysis of Neighborhood Environmental Stress in Relation to Biological Markers of Cardiovascular Health and Health Behaviors in Women: Protocol for a Pilot Study.

BackgroundInnovative analyses of cardiovascular (CV) risk markers and health behaviors linked to neighborhood stressors are essential to further elucidate the mechanisms by which adverse neighborhood social conditions lead to poor CV outcomes. We propose to objectively measure physical activity (PA), sedentary behavior, and neighborhood stress using accelerometers, GPS, and real-time perceived ecological momentary assessment via smartphone apps and to link these to biological measures in a sample of White and African American women in Washington, DC, neighborhoods.ObjectiveThe primary aim of this study is to test the hypothesis that living in adverse neighborhood social conditions is associated with higher stress-related neural activity among 60 healthy women living in high or low socioeconomic status neighborhoods in Washington, DC. Sub-aim 1 of this study is to test the hypothesis that the association is moderated by objectively measured PA using an accelerometer. A secondary objective is to test the hypothesis that residing in adverse neighborhood social environment conditions is related to differences in vascular function. Sub-aim 2 of this study is to test the hypothesis that the association is moderated by objectively measured PA. The third aim of this study is to test the hypothesis that adverse neighborhood social environment conditions are related to differences in immune system activation.MethodsThe proposed study will be cross-sectional, with a sample of at least 60 women (30 healthy White women and 30 healthy Black women) from Wards 3 and 5 in Washington, DC. A sample of the women (n=30) will be recruited from high-income areas in Ward 3 from census tracts within a 15% of Ward 3’s range for median household income. The other participants (n=30) will be recruited from low-income areas in Wards 5 from census tracts within a 15% of Ward 5’s range for median household income. Finally, participants from Wards 3 and 5 will be matched based on age, race, and BMI. Participants will wear a GPS unit and accelerometer and report their stress and mood in real time using a smartphone. We will then examine the associations between GPS-derived neighborhood variables, stress-related neural activity measures, and adverse biological markers.ResultsThe National Institutes of Health Institutional Review Board has approved this study. Recruitment will begin in the summer of 2021.ConclusionsFindings from this research could inform the development of multilevel behavioral interventions and policies to better manage environmental factors that promote immune system activation or psychosocial stress while concurrently working to increase PA, thereby influencing CV health.International Registered Report Identifier (IRRID)PRR1-10.2196/29191

Developing an animal-assisted support program for healthcare employees

BackgroundEmployee burnout and its associated consequences is a significant problem in the healthcare workforce. Workplace animal therapy programs offer a potential strategy for improving employee well-being; however, research on animal therapy programs for healthcare workers is lacking. This study aimed to evaluate the feasibility, acceptability and preliminary impact of an animal-assisted support program to improve healthcare employee well-being.MethodsIn this mixed-methods pilot intervention study, we implemented an animal-assisted support program in a multidisciplinary healthcare clinic at a large VA hospital. The program included 20 sessions over 3 months, each approximately 1-h long. Real-time mood data were collected from participants immediately before and after each session. Participation rates were tracked in real time and self-reported at follow-up. Data on burnout and employee perceptions of the program were collected upon completion via a survey and semi-structured interviews. Differences in mood and burnout pre/post program participation were assessed with t-tests.ResultsParticipation was high; about 51% of clinic employees (n = 39) participated in any given session, averaging participation in 9/20 sessions. Mood (on a scale of 1 = worst to 5 = best mood) significantly improved from immediately before employees interacted with therapy dogs (M = 2.9) to immediately after (M = 4.5) (p = 0.000). Employees reported significantly lower levels of patient-related burnout (e.g., how much exhaustion at work relates to interaction with patients) after (M = 18.0 vs. before, M = 40.0) participating (p = 0.002). Qualitative findings suggested that employees were highly satisfied with the program, noticed an improved clinic atmosphere, and experienced a reduction in stress and boost in mood.ConclusionsEstablishing an animal-assisted support program for employees in a busy healthcare clinic is feasible and acceptable. Our pilot data suggest that animal-assisted programs could be a means to boost mood and decrease facets of burnout among healthcare employees.

Meezaj: An Interactive System for Real-Time Mood Measurement and Reflection based on Internet of Things

Subjective well-being has a critical affect on progress and productivity vital for digital and strategical trans-formation. Increase in the suicide attempts of the college and university students is a clear indication of stress and anxiety among the students. Offering a fulfilling and healthy life to promote the life-long learning journey is also one of the important objectives of the Vision 2030 for modernization of the Kingdom of Saudi Arabia. Due to the multifaceted nature of subjective well-being, real-time mood measurement and reflection is a challenging task and demands using latest technologies. This paper aims to present Meezaj, an interactive system for real-time mood measurement and reflection leveraging the Internet of Things (IoT) technology. Architecture and workflow of the Meezaj system are discussed in detail. Meezaj not only promotes the sense of significance in the students, by indicating that their happiness matters in decision making, but also assists policy makers to identify factors affecting the happiness in an educational institute.

Testing the Feasibility of Using Ecological Momentary Assessment to Collect Real-Time Behavior and Mood to Predict Technology-Measured HIV Medication Adherence.

Identifying distinct patterns of behavior and mood in natural environments that interrupt medication adherence among individuals with HIV will be useful in informing intervention development. This pilot study assessed the initial efficacy of using ecologic momentary assessment to define patterns of alcohol use, mood, and medication adherence. Participants reported intraday alcohol use and mood using app-enabled smartphones and MEMSCap pill bottles to measure medication adherence. There were 34 enrolled participants, 29 of whom completed the 28-day study. Participants drank a mean of 7.75days of the study period. The positive and negative affect scores ranged from 10 to 50, with a mean of 25.7 and 11.4 for each, respectively. The average medication adherence for the sample was 94.1%. These findings suggest these types of data collection methods are increasingly acceptable in measuring real-time mood and behavior, which may better inform interventions addressed at increasing HIV adherence practices.

Associations between marijuana use and anxious mood lability during adolescence

ObjectiveTo date, research investigating the association between adolescent marijuana use and anxiety is mixed, given differences in how anxiety is measured and the age ranges studied. The research is further limited as many relevant studies have small sample sizes. This investigation examines the association between marijuana use (use in the past 30 days) and anxious mood lability (rapid fluctuation in emotional states) during early adolescence (average age 14.4, spring of 8th grade) through midadolescence (10th grade). MethodsParticipating adolescents (N = 466; 52.8% female) were from rural and suburban communities and 38% were Hispanic/Latino. Ecological Momentary Assessment (EMA) was used to measure adolescents' anxious mood in real time; the EMAs were collected within 30 days of the adolescent report of their marijuana use. ResultsMultilevel models with measurement waves (7 time points) nested in individuals showed that anxious mood lability was significantly higher for adolescents reporting recent marijuana use compared to those reporting no recent marijuana use. Although females were higher than males in anxious mood lability, the association between anxious mood lability and recent marijuana use did not differ by gender. Post hoc analysis showed that the associations between anxious mood lability and recent marijuana use did not differ between assessments conducted pre and post legalization of adult recreational marijuana use. ConclusionsThe association between recent marijuana use and anxious mood lability for youth is important for understanding the developmental processes of cannabis use and anxious mood disorders in adolescence and young adulthood.

Microblog sentiment analysis with weak dependency connections

With the rise of microblogging services like Twitter and Sina Weibo, users are able to post their real-time mood and opinions conveniently and swiftly. At the same time, the ubiquitous social media results in abundant social relations such as following and follower relations. Social relations create a new source for microblog sentiment analysis, which attracts a great amount of attention in recent years. There are two theories that support the use of social relations for sentiment analysis - sentiment consistency and emotional contagion. However, most existing microblog sentiment analysis methods only employ direct connections which cannot fully use the heterogeneous connections in social media. As online social networks consist of communities and nodes in the same community which form weak dependency connections usually share similarities, we investigate how to exploit weak dependency connections as an aspect of social contexts for microblog sentiment analysis in this paper. In particular, we employ community detection methods to capture weak dependency connections and propose a new model for microblog sentiment analysis which incorporates weak dependency connections, sentiment consistency, and emotional contagion together with text information. Experimental results on two real Twitter datasets demonstrate that our proposed model can outperform baseline methods consistently and significantly.

Exercise versus Nonexercise Activity: E-diaries Unravel Distinct Effects on Mood.

The association between physical activity and mood is of major importance to increase physical activity as a prevention strategy for noncommunicable diseases and to improve mental health. Unfortunately, existing studies examining how physical activity and mood wax and wane within persons over time in everyday life do show ambiguous findings. Taking a closer look at these studies reveals that the aggregation levels differ tremendously. Whereas mood is conceptualized as a three-dimensional construct, physical activity is treated as a global construct not taking into account its distinct components like exercise (such as jogging) and nonexercise activity (NEA; such as climbing stairs). To overcome these limitations, we conducted an ambulatory assessment study on the everyday life of 106 adults over 7 d continuously measuring NEA via accelerometers and repeatedly querying for mood in real time via GPS-triggered e-diaries. We used multilevel modeling to derive differential within-subject effects of exercise versus NEA on mood and to conduct analyses on the temporal course of effects. Analyses revealed that exercise increased valence (beta = 0.023; P < 0.05) and calmness (beta = 0.022; P < 0.05). A tendency of decreasing energetic arousal (beta = -0.029) lacked significance. NEA, parameterized as 15-min episodes of physical activity intensity in everyday life, increased energetic arousal (beta = 0.135; P < 0.001) and decreased calmness (stand. beta = -0.080; P < 0.001). A tendency of increasing valence (beta = 0.014) lacked significance. Using longer time intervals for NEA revealed similar findings, thus confirming our findings. Exercise and NEA differed regarding their within-subject effects on mood, whereas exercise increased valence and calmness, NEA increased energetic arousal and decreased calmness. Therefore, it appears necessary to clearly differentiate between exercise and NEA regarding their within-subject effects on mood dimensions in both research and treatment.

Impact of alcohol use motives and internalizing symptoms on mood changes in response to drinking: An ecological momentary assessment investigation

BackgroundTheory implies that individuals who use alcohol to cope with negative emotions experience the acute mood-altering effects they desire. However, no study to date has directly tested whether alcohol coping motives map onto alcohol-induced changes in mood in real-time or how co-occurring internalizing symptoms (i.e., depression and anxiety) impact the relation between coping motives and alcohol-induced changes in mood. MethodThe current study tested the unique and interactive effects of alcohol coping motives and internalizing symptoms on mood changes during drinking using ecological momentary assessment (EMA) in a sample of young adults (n=257). Participants completed a battery of questionnaires and a 7-day EMA assessment protocol. ResultsIn general, alcohol use was associated with greater positive mood and reduced negative mood while drinking. However, individuals who reported that they use alcohol to cope with anxiety, but not depression, experienced less mood benefits from alcohol relative to those without mood coping motives. In contrast, individuals with high internalizing symptoms experienced greater mood benefits while drinking relative to those with low levels of internalizing symptoms; and at high levels of anxiety, alcohol consumption was reinforcing for everyone regardless of coping motives. Only at low levels of anxiety symptoms, did coping with anxiety motives attenuate alcohol’s acute reinforcing effects. ConclusionsThese results together confirm that alcohol has a robust impact on real-time mood in young adults and sheds light on the processes that may contribute to repeated alcohol use within individuals who do, and do not, use alcohol as a means of coping.

The Effects of Four-Week Multivitamin Supplementation on Mood in Healthy Older Women: A Randomized Controlled Trial.

Objective. Nutritional deficiencies have been associated with cognitive decline and mood disturbances. Vitamin intake can influence mood and randomized controlled trials have demonstrated that multivitamin supplements are capable of reducing mild symptoms of mood dysfunction. However, few studies have focussed on healthy older women. Methods. This study investigated the effects of four weeks' multivitamin supplementation on mood in 76 healthy women aged 50–75 years. Mood was assessed before and after intervention in the laboratory using measures of current mood and retrospective experiences of mood over the past week or longer. Mobile phones were used to assess changes in real-time mood ratings, twice weekly in the home. Results. There were no multivitamin-related benefits identified for measures of current mood or reflections of recent mood when measured in the laboratory. In-home assessments, where mood was rated several hours after dose, revealed multivitamin supplementation improved ratings of stress, with a trend to reduce mental fatigue. Conclusions. Over four weeks, subtle changes to stress produced by multivitamin supplementation in healthy older women may not be detected when only pre- and posttreatment mood is captured. In-home mobile phone-based assessments may be more sensitive to the effects of nutritional interventions compared to traditional in-laboratory assessments.

Style changes in time‐coded stream‐of‐consciousness handwriting identifies real‐time mood fluctuations in mania (728.19)

Methods to experimentally assess changes in mood are limited. In this case study real‐time mood fluctuations in mania were measured by evaluating, without regard to content, changes in time‐coded stream‐of‐consciousness writing style during a 29‐day manic episode experienced and recorded by one of the authors (nlc). Mood was judged to be in flux when text script changed from linear to non‐linear with the time point of the change being the cusp between the two writing styles. Handwritten in 13 bound journals were 54,580 words, with 21,918 of them (40%) written in the episode’s first quadrant, 16,287 (30%) in the second, 10,475 (20%) in the third, and 5,900 (10%) in the final quadrant. There were 195 writing style cusps, with 17% occurring in the first quadrant, 48% in the second, 30% in the third, and 5% in the fourth. These time‐coded writing style cusps denoted real‐time mood fluctuations during the manic episode. Even though the most words were written in the first quadrant, mood fluctuations as measured by writing style cusps were greatest in the second quadrant. This case study demonstrates that mood fluctuations in mania can be objectively studied by analyzing time‐coded stream‐of‐consciousness handwriting. Comparison of writing style cusps across time could help evaluate mania mood fluctuations to determine the need for or the efficacy of pharmaceutical and/or behavioral management protocols.

Mood Regulation in Real Time

Mechanisms have been proposed to underlie differences between younger and older adults in real-time mood regulation, but these mechanisms have not yet been shown to predict mood outcomes. One such mechanism is age-related positivity effects in attention and memory. In this article, I take one form of this possible mechanism—positive looking patterns—and consider (a) whether older adults, compared with younger adults, prefer positive looking and (b) whether positive looking helps older adults regulate their mood in real time. Evidence is more consistent for the former than the latter. A similar consideration is needed for other possible forms of positivity effects (e.g., positive memory) and other possible mechanisms that may explain age differences in real-time mood regulation.

Deliberate real-time mood regulation in adulthood: The importance of age, fixation and attentional functioning

While previous research has linked executive attention to emotion regulation, the current study investigated the role of attentional alerting (i.e., efficient use of external warning cues) on younger (N=39) and older (N=44) adults’ use of gaze to regulate their mood in real time. Participants viewed highly arousing unpleasant images while reporting their mood and were instructed to deliberately manage how they felt and to minimise the effect of those stimuli on their mood. Fixations toward the most negative areas of the images were recorded with eye tracking. We examined whether looking less at the most negative regions, compared to each individual's own tendency, was a beneficial mood regulatory strategy and how it interacted with age and alerting ability. High alerting older adults, who rely more on external cues to guide their attention, experienced a smaller decline in mood over time by activating a less-negative-looking approach (compared to their own average tendency), effectively looking away from the most negative areas of the images. More negative gaze patterns predicted better mood for younger adults, though this effect decreased over time. Alerting did not moderate gaze–mood links in younger adults. Successful mood regulation may thus depend on particular combinations of age, fixation, and attention.