Mood detection and prediction using conventional machine learning techniques on COVID19 data.

Emotion detection is a promising field of research in multiple perspectives such as psychology, marketing, network analysis and so on. Multiple models have been suggested over the years for accurate and efficient mood detection. Identifying emotion, or mood, from text has progressed from a simple frequency distribution analysis to far more complicated learning approaches. The main aim of all these text mining and analysis is twofold. First is to categorise existing text into broad classes of emotions, such as happy, sad, angry, surprised and so on. The second aim is to accurately predict the moods of real-time streaming text. The novelty of the work lies in the extensive comparison of nine conventional learning methods with respect to performance metrics precision, recall, F1 and accuracy as well as studying the variance of mood over time using a wide array of moods (25). Using conventional classifiers allow near real-time predictions, can work on considerably less training data, and has the flexibility of feature engineering, as deep learning methods have feature engineering embedded in the model. Since a single line of text can be associated with multiple emotions, this article compares the performance of classifiers in predicting multiple moods for streaming text with likelihood-based ranking. An android application named Citizens' Sense was developed for text collection and analysis. The performance of mood classifiers are tested further using Twitter data related to COVID19. Based on the precision, recall, F1 and accuracy of the classifiers, it can be seen that Random Forest, Decision Tree and Complement Naive Bayes classifiers are marginally better than the other classifiers. The variance of mood over time, and predicted moods for text support this finding.

Spatio-temporal variation of Covid-19 health outcomes in India using deep learning based models.

Deep learning methods have become the state of the art for spatio-temporal predictive analysis in a wide range of fields, including environmental management, public health, urban planning, pollution monitoring, and so on. Despite the fact that a variety of powerful deep learning-based models can address various problem-specific issues in different research domain, it has been found that no single optimal model can outperform everywhere. Now, in the last two years, various deep learning-based studies have provided a variety of best-performing techniques for predicting COVID-19 health outcomes. In this context, this study attempts to perform a case study that investigates the spatio-temporal variation in the performance of deep-learning-based methods for predicting COVID-19 health outcomes in India. Various widely applied deep learning models namely CNN (convolutional neural network), RNN (recurrent neural network), Vanilla LSTM (long short-term memory), LSTM Autoencoder, and Bidirectional LSTM are considered to investigate their spatio-temporal performance variation. The effectiveness of the models is assessed using various metrics based on COVID-19 mortality time-series from 36 states and union territories of India.

Pollutant specific optimal deep learning and statistical model building for air quality forecasting.

Poor air quality is becoming a critical environmental concern in different countries over the last several years. Most of the air pollutants have serious consequences on human health and wellbeing. In this context, efficient forecasting of air pollutants is currently crucial to predict future events with a view to taking corrective actions and framing effective environmental policies. Although deep learning (DL) as well as statistical forecasting models are investigated in the literature, they have rarely used in air pollutant-specific optimal model building for long-term forecasting. In this paper, our aim is to develop the pollutant-specific optimal forecasting models for the phases spanning from preprocessing to model building by investigating a set of predictive techniques. In this regard, this paper presents a methodology for long-term forecasting of some important air pollutants. More specifically, a total of eight best performing models such as stacked LSTM, LSTM auto-encoder, Bi-LSTM, convLSTM, Holt-Winters, auto-regressive (AR), SARIMA, and Prophet are investigated for developing pollutant-specific optimal forecasting models. The study is carried out based on the real-world data obtained from government-run air quality monitoring units in Kolkata over a period of 4 years. The models such as Holt-Winters, Bi-LSTM, and ConvLSTM achieve high forecasting accuracy with respect to MAE and RMSE values for majority of the pollutants.

Impact of second-order network motif on online social networks.

The behaviour of individual users in an online social network is a major contributing factor in determining the outcome of multiple network phenomenon. Group formation, growth of the network, information propagation, and rumour blocking are some of the many network behavioural traits that are influenced by the interaction patterns of the users in the network. Network motifs capture one such interaction pattern between users in online social networks (OSNs). For this work, four second-order (two-edged) network motifs have been considered, namely, message receiving pattern, message broadcasting pattern, message passing pattern, and reciprocal message pattern, to analyse user behaviour in online social networks. This work provides and utilizes a node interaction pattern-finding algorithm to identify the frequency of aforementioned second-order network motifs in six real-life online social networks (Facebook, GPlus, GNU, Twitter, Enron Email, and Wiki-vote). The frequency of network motifs participated in by a node is considered for the relative ranking of all nodes in the online social networks. The highest-rated nodes are considered seeds for information propagation. The performance of using network motifs for ranking nodes as seeds for information propagation is validated using statistical metrics Z-score, concentration, and significance profile and compared with baseline ranking methods in-degree centrality, out-degree centrality, closeness centrality, and PageRank. The comparative study shows the performance of centrality measures to be similar or better than second-order network motifs as seed nodes in information diffusion. The experimental results on finding frequencies and importance of different interaction patterns provide insights on the significance and representation of each such interaction pattern and how it varies from network to network.

Social Injustice in the Neoliberal Pandemic Era for Homeless Persons With Mental Illness: A Qualitative Inquiry From India.

The Corona Virus Disease 2019 (COVID-19) pandemic has presented an unprecedented challenge globally. It is much bigger than a bio-medical concern now with the multitudes of socio-economic, socio-political, socio-cultural, and psycho-social impact, which are likely to outlast the pandemic itself by far and long. The pandemic and the resulting challenges across societies highlighted the existing social injustices in a neoliberal world for historically marginalized populations like homeless persons with mental illness (HPMI). The nationwide lockdown in India to resist the spread of the virus posed a unique challenge to this vulnerable population. The present study thus attempts to understand the experience of HPMI during the COVID-19 induced lockdown through the theoretical framework of social justice vis-à-vis injustice. Semi-structured interviews have been conducted on seven HPMI rehabilitated in the community through an NGO situated in Kolkata, India. Seven stakeholders have also been interviewed to understand their experience in providing services to the HPMI during the COVID-19 induced lockdown. Analyses of the narratives have been done using initial coding, focused coding and axial coding through the process of constant comparison of constructivist grounded theory (CGT) methodology. Critical insights from the study bring out experiences of HPMI during COVID-19 as a victim of structural violence, highlighting their exclusion and victimization due to the existing marginalized status, living closer to the edge as a consequence of the lockdown, lack of awareness of the gravity of the pandemic situation. The experiences of the stakeholders, on the other hand, pointed out the role of community members and social workers in partially mitigating the challenges. This study indicates that to mitigate the aftermaths, stakeholders, including community members, need to work together for rebuilding and enhancing the strength and resilience of the marginalized populations like HPMI, who are historically victims of social injustice in the neoliberal pandemic era.

Geographically varying relationships of COVID-19 mortality with different factors in India.

COVID-19 is a global crisis where India is going to be one of the most heavily affected countries. The variability in the distribution of COVID-19-related health outcomes might be related to many underlying variables, including demographic, socioeconomic, or environmental pollution related factors. The global and local models can be utilized to explore such relations. In this study, ordinary least square (global) and geographically weighted regression (local) methods are employed to explore the geographical relationships between COVID-19 deaths and different driving factors. It is also investigated whether geographical heterogeneity exists in the relationships. More specifically, in this paper, the geographical pattern of COVID-19 deaths and its relationships with different potential driving factors in India are investigated and analysed. Here, better knowledge and insights into geographical targeting of intervention against the COVID-19 pandemic can be generated by investigating the heterogeneity of spatial relationships. The results show that the local method (geographically weighted regression) generates better performance ([Formula: see text]) with smaller Akaike Information Criterion (AICc [Formula: see text]) as compared to the global method (ordinary least square). The GWR method also comes up with lower spatial autocorrelation (Moran's [Formula: see text] and [Formula: see text]) in the residuals. It is found that more than 86% of local [Formula: see text] values are larger than 0.60 and almost 68% of [Formula: see text] values are within the range 0.80-0.97. Moreover, some interesting local variations in the relationships are also found.

Long-term time-series pollution forecast using statistical and deep learning methods.

Tackling air pollution has become of utmost importance since the last few decades. Different statistical as well as deep learning methods have been proposed till now, but seldom those have been used to forecast future long-term pollution trends. Forecasting long-term pollution trends into the future is highly important for government bodies around the globe as they help in the framing of efficient environmental policies. This paper presents a comparative study of various statistical and deep learning methods to forecast long-term pollution trends for the two most important categories of particulate matter (PM) which are PM2.5 and PM10. The study is based on Kolkata, a major city on the eastern side of India. The historical pollution data collected from government set-up monitoring stations in Kolkata are used to analyse the underlying patterns with the help of various time-series analysis techniques, which is then used to produce a forecast for the next two years using different statistical and deep learning methods. The findings reflect that statistical methods such as auto-regressive (AR), seasonal auto-regressive integrated moving average (SARIMA) and Holt-Winters outperform deep learning methods such as stacked, bi-directional, auto-encoder and convolution long short-term memory networks based on the limited data available.

Evaluating a community based mental health programme in West Bengal, India: Description of the methodology and lessons learned.

Mental disorders impose an enormous burden on society. In developing countries like India, there is a lack of adequate number of trained mental health professionals to provide specialized care and 75-85 % of affected individuals do not have access to appropriate mental health services. The National Mental Health Programme (NMHP) is being implemented by the Government of India to support state governments in providing mental health services in the country. The Urban Mental Health Programme (UMHP) is a pilot initiative that has attempted the integration of mental health services in primary health care settings in two municipal wards in Kolkata, West Bengal, India. The overarching aim of this paper is to describe the methodology used for the evaluation of the community based mental health programme and to understand the processes of the programme in terms of barriers and facilitators. The current evaluation is based on a concurrent nested design, where qualitative and quantitative data are both collected at the same time but analysed separately and priority was given to qualitative data. This experience will contribute in helping other researchers to make some evaluations more effective, useful and manageable. Ethics approval was obtained from an institutional ethics committee of an organization (Ekjut) based in Ranchi, Jharkhand, India. The evaluation was undertaken by the George Institute for Global Health, New Delhi from February- June 2016.

PPARγ antagonist GW9662 induces functional estrogen receptor in mouse mammary organ culture: potential translational significance.

The nuclear receptor peroxisome proliferator-activated receptor gamma (PPARγ) plays a central role in regulating metabolism, including interaction with the estrogen receptor-α (ERα). Significantly, PPARγ activity can be modulated by small molecules to control cancer both in vitro and in vivo (Yin et al., Cancer Res 69:687-694, 2009). Here, we evaluated the effects of the PPARγ agonist GW7845 and the PPARγ antagonist GW9662 on DMBA-induced mammary alveolar lesions (MAL) in a mouse mammary organ culture. The results were as follows: (a) the incidence of MAL development was significantly inhibited by GW 7845 and GW 9662; (b) GW9662 but not GW7845, in the presence of estradiol, induced ER and PR expression in mammary glands and functional ERα in MAL; (c) while GW9662 inhibited expression of adipsin and ap2, GW 7845 enhanced expression of these PPARγ-response genes; and (d) Tamoxifen caused significant inhibition of GW9662 treated MAL, suggesting that GW9662 sensitizes MAL to antiestrogen treatment, presumably through rendering functional ERα and induction of PR. The induction of ERα by GW9662, including newer analogs, may permit use of anti-ER strategies to inhibit breast cancer in ER- patients.

Response surface optimization of sustained release metformin-hydrochloride matrix tablets: influence of some hydrophillic polymers on the release.

The aim of the present work was designed to develop a model-sustained release matrix tablet formulation for Metformin hydrochloride using wet granulation technique. In the present study the formulation design was employed to statistically optimize different parameters of Metformin hydrochloride tablets at different drug-to-polymer ratios employing polymers Hydroxypropyl methylcellulose of two grades K4M and K100M as two independent variables whereas the dependent variables studied were X(60), X(120), T(50), T(90), n, and b values obtained from dissolution kinetics data. The in vitro drug release studies were carried out at simulated intestinal fluids, and the release showed a non-Fickian anomalous transport mechanism. The drug release was found to reveal zero order kinetics. The granules and the tablets were tested for their normal physical, morphological, and analytical parameters and were found to be within the satisfactory levels. There were no significant drug-polymer interactions as revealed by infrared spectra. It has been found out that on an optimum increased Hydroxypropyl methylcellulose K100M concentration and decreased Hydroxypropyl methylcellulose K4M concentration the formulations were elegant in terms of their release profiles and were found to be statistically significant and generable.

Regulation of CYP24 splicing by 1,25-dihydroxyvitamin D3 in human colon cancer cells.

CYP24 is a well-established vitamin D receptor (VDR) target gene. The active VDR ligand 1,25(OH)2D3 regulates its own catabolism by increasing CYP24 expression. It is well known that in the presence of 1,25(OH)2D3, VDR binds to VDREs in the promoter region of CYP24 and initiates CYP24 transcription. However, little is known about the role of 1,25(OH)2D3 in the posttranscriptional modulation of CYP24. In this study, we investigated the functional significance of 1,25(OH)2D3 in CYP24 RNA splicing in colon cancer cells. Using RT-PCR, we found that 1,25(OH)2D3 actively induces CYP24 splicing in a time-dependent manner and CYP24 splicing pattern could be cell type or tissue specific. The induction of RNA splicing by 1,25(OH)2D3 was mainly CYP24 selective. Treatment of cells with parathyroid hormone inhibited basal CYP24 splicing, but failed to inhibit 1,25(OH)2D3-induced CYP24 splicing. Further experiments demonstrated that new RNA synthesis was required for the induction of CYP24 splicing by vitamin D. In addition, alteration of multiple signaling pathways also affected CYP24 splicing and cellular sensitivity in response to vitamin D appeared to correlate with the induction of CYP24 splicing. These results suggest that 1,25(OH)2D3 not only regulates CYP24 transcription, but also plays an important role in posttranscriptional modulation of CYP24 by inducing its splicing. Our findings reveal an additional regulatory step that makes the vitamin D mediated action more prompt and efficient.