pornpimol chaiwuttisak - Academia.edu (original) (raw)
Papers by pornpimol chaiwuttisak
The Journal of Applied Science
The research aimed to compare the accuracy of forecasting methods for daily incoming call volume.... more The research aimed to compare the accuracy of forecasting methods for daily incoming call volume. There were three forecasting methods that were used in the study: Box-Jenkins method with SRIMA model and SARIMAX model, Artificial Neural Network (ANN) model and the hybrid model combining SARIMAX and Artificial Neural Network (SARIMAX-ANN) model. The data used in this study is time series of daily incoming call volume to call center which can be divided into 2 data sets. The first data set which was the past data from January 2016 to December 2018 were used for selecting of the most suitable model and the second data set was the past data from January 2019 to December 2019 for the comparison of the accuracy of forecasting model by using Mean Absolute Percentage Error (MAPE). The results showed model with the lowest MAPE is hybrid model of SARIMAX-ANN (MAPE = 24.02%), while the MAPE values for SARIMAX, ANN and SARIMA were 24.06%, 43.70%, and 44.97% respectively. It indicates that the hybrid model is more accurate in forecasting than individual model. The hybrid model can be used to forecast daily incoming call volume which is supporting information for the suitable workforce planning of customer service center in the future.
2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)
The objectives of this study were the following: (1) to investigate the correlations between data... more The objectives of this study were the following: (1) to investigate the correlations between data collected through Internet of Thing (IOT) and unintentional behavior of drivers (2) to create the models based on machine learning techniques to classify unintentional behavior of drivers who drive the natural gas vehicle and (3) to compare the forecasting accuracy of the learning model. Data studied were collected from the system of the natural gas transportation business in Thailand. There were 10,693 records starting from January 1, 2019 to December 31, 2019, for a period of 12 months. Moreover, KNIME Analytics Platform was used to create the model. The research findings were as follows: (1) duration time when the driver is not looking straight, driving speeds, distance coverage of the driver faces that is not looking straight detecting by a camera and the latitude and longitude coordinates have a relationship with unintentional behavior of the driver; and (2) Neural Network with two hidden layer and 5 neurons in the hidden layer performs the highest accuracy (873%), followed by Support Vector Machine with S3.9%, of accuracy. It can be said that Neural Network can be used to create an efficient predictive model.
The Journal of King Mongkut's University of Technology North Bangkok, 2022
2018 5th International Conference on Business and Industrial Research (ICBIR), 2018
Football is considered one of the most popular sports in Thailand and has high influence on the n... more Football is considered one of the most popular sports in Thailand and has high influence on the nation economy. Thai Premier League is football competition at the top of Thai football league system. The objective of the paper is to evaluate both sportive and financial efficiency of football clubs in Thai Premier League during 2014-2015 football seasons with Data Envelopment Analysis (DEA) model: CCR DEA and super- efficiency DEA. We consider three input factors: the stadium capacity, the capital Investment, the administrative expenses. Nine output variables investigated on the efficiency of football clubs are the number of supportive attendances, the total score in 2015, the total revenues, net assets, the number of trophies, the qualification for AFC for the last and the next season, the qualification for Thai Premier League for the last and the next season. The results show that two football clubs are not efficient. Later, it is found that both football clubs mentioned are relegated to lower league in the next competition 2016/2017. This evidence illustrates that super-efficiency DEA models can be successively to distinguish the efficient clubs and rank the football clubs in Thai Premier League.
When referring to this work, full bibliographic details including the author, title, awarding ins... more When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given e.g.
2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST), 2021
We consider a vehicle routing problem starting from a depot to serve customers whose demands are ... more We consider a vehicle routing problem starting from a depot to serve customers whose demands are deterministic using company vehicles. However, the capacities of their own vehicles cannot fulfill all customer demands. Thus, the company must hire vehicles with several vehicle types, each type being defined by a capacity. All company vehicles must return back to the depot, while hiring vehicles do not have to come back to the depot in order to achieve the objective of the minimum total travel distance. This mentioned characteristic of the problem are called Homogeneous Fixed Fleet Close Open Mixed Vehicle Routing Problem (HFFCOMVRP) which is an NP-Hard problem. Therefore, this research presents applying ant colony optimization which is meta-heuristic algorithms for solving complex optimization problems to find good solutions with acceptance in computation time. The algorithm presented is developed in Python and then tested against 15 standard problems of Augerat et al. (1995). The ant colony optimization with improving the solution using 2-Opt and one-move heuristics is efficient in simultaneously determining the open and close routes in the solutions with a wide range of vehicle capacities. It provides the best solution for 12 out of 15 problems
World Academy of Science, Engineering and Technology, International Journal of Mathematical and Computational Sciences, 2016
Decision making on facility locations for blood services and blood distribution plan has an impac... more Decision making on facility locations for blood services and blood distribution plan has an impact on the efficiency of blood supply chain and logistics systems. In the blood supply chain operated by the Thai Red Cross Society (TRCS), problems are faced with amounts of blood collected in different provinces of Thailand being insufficient to meet demand. A proposal has been made to extend this network of blood centres using low-cost collection and distribution centres. Increasing numbers of fixed collection sites can improve access for donors. In addition, some facilities can perform preparation and storage for blood that hospitals can receive directly. Selecting sites for these two types of facility within a limited investment budget informs the strategic plan of this non-profit organisation. Furthermore, we consider the blood delivery problem to hospitals under variable and insufficient supplies of blood. Hospitals are assigned either to fixed routes or variable routes according to...
The objectives of this research were to analyze the relationship of the phrases or words commonly... more The objectives of this research were to analyze the relationship of the phrases or words commonly found in the comments from depression hashtag on Twitter using the association rules. The data used in this study were collected from comments in Thai language via depression hashtag on Twitter during 1 January 2019 to 31 January 2019, in total of 1,500 comments. According to the comments in Thai language on social media collected by using Rapidminer Studio 9 software to get the word about depression and used to analyze relationships of words from a text comment to get the format data Association. The frequency of words and phrases in a form of presentation is used to describe the various opinions about the depression that has a presentation on social media. According to the model performance in each of the above methods, it was found that Euclidean Distance provided the best result due to the smallest average distance at all points in each cluster which was equal to 152.504. The associ...
Proceedings of the 2019 2nd International Conference on Mathematics and Statistics - ICoMS'19, 2019
The objective of this research is to evaluate the relative performance efficiency and determine t... more The objective of this research is to evaluate the relative performance efficiency and determine the factors affecting the efficiency of 11 police stations in the Metropolitan Police Division 3. The first stage is to analyze the efficiency of the police station by Data Envelopment Analysis (DEA) that measures the variable return to scale (VRS) and considering output-orientation. Input variable is the number of police officers. Output variables are the percentage of arrests with remand in custody, from the total amount of arrests, the percentage of arrests with remand in traffic offences, from the total amount of traffic offences, an average score of people's satisfaction on facilities of the police station, operational processes and the service of the staffs. Secondary data are collected from 11 police stations during January and December 2017, for a total of one year. Primary data, which are the satisfaction score, are obtained from the sample survey. For the second stage, the f...
Journal of Physics: Conference Series, 2021
This research objective is to study the latent topics analysis in selling post of real estate of ... more This research objective is to study the latent topics analysis in selling post of real estate of second-hand condominium by using Latent Dirichlet Allocation (LDA) and build a price prediction model of second-hand condominium using multiple linear regression and artificial neural networks by measuring and comparing the performance of the second hand condominium price prediction model with root mean square error (RMSE). This experiment included four variables are room size, number of bathroom, number of bedroom and latent topics from LDA. The result of LDA indicated that selling post of real estate can be separated into 4 topics, in which finding the factors that affect the price use the regression analysis method to get five variables are room size, number of bathroom, floors, topic 2 and topic 4. The RMSE based on the multiple linear regression analysis was 1.349, while the RMSE based on artificial neural network was 1.156. Thus, it can be concluded that the predictive model using ...
Computational Science and Its Applications – ICCSA 2021, 2021
Studies in Computational Intelligence, 2020
The objectives of this research were to analyze the relationship of the phrases or words commonly... more The objectives of this research were to analyze the relationship of the phrases or words commonly found in the comments from depression hashtag on Twitter using the association rules. The data used in this study were collected from comments in Thai language via depression hashtag on Twitter during 1 January 2019 to 31 January 2019, in total of 1,500 comments. According to the comments in Thai language on social media collected by using Rapidminer Studio 9 software to get the word about depression and used to analyze relationships of words from a text comment to get the format data Association. The frequency of words and phrases in a form of presentation is used to describe the various opinions about the depression that has a presentation on social media. According to the model performance in each of the above methods, it was found that Euclidean Distance provided the best result due to the smallest average distance at all points in each cluster which was equal to 152.504. The association analysis, a total of 30 association rules were obtained, the support of 0.5% and the 80% confidence.
Operations Research for Health Care, 2016
Decision making on facility locations for blood services has an impact on the efficiency of suppl... more Decision making on facility locations for blood services has an impact on the efficiency of supply chain and logistics systems. In the blood supply chain operated by the Thai Red Cross Society (TRCS), problems are faced with amounts of blood collected in different provinces of Thailand being insufficient to meet demand. At the present time, TRCS operates one National Blood Centre in the capital and twelve Regional Blood Centres in different provinces to collect, prepare, test, and distribute safe blood. A proposal has been made to extend this network of blood centres using low-cost collection and distribution centres. Increasing numbers of fixed collection sites can improve access for donors. In addition, some facilities will be able to perform preparation and storage for blood that hospitals can receive directly. This paper addresses the selection of sites for two types of facility, either a blood donation room only or donation room with a distribution centre. A range of investment budgets is investigated to inform the strategic plan of this non-profit organisation. We present a novel binary integer programming model for this location-allocation problem based on objectives of improving the supply of blood products while reducing costs of transportation. Computational results are reported, using real life data, that are of practical importance to decision makers.
Health Care Management Science, 2017
As an aid to predicting future hospital admissions, we compare use of the Multinomial Logit and t... more As an aid to predicting future hospital admissions, we compare use of the Multinomial Logit and the Utility Maximising Nested Logit models to describe how patients choose their hospitals. The models are fitted to real data from Derbyshire, United Kingdom, which lists the postcodes of more than 200,000 admissions to six different local hospitals. Both elective and emergency admissions are analysed for this mixed urban/rural area. For characteristics that may affect a patient's choice of hospital, we consider the distance of the patient from the hospital, the number of beds at the hospital and the number of car parking spaces available at the hospital, as well as several statistics publicly available on National Health Service (NHS) websites: an average waiting time, the patient survey score for ward cleanliness, the patient safety score and the inpatient survey score for overall care. The Multinomial Logit model is successfully fitted to the data. Results obtained with the Utility Maximising Nested Logit model show that nesting according to city or town may be invalid for these data; in other words, the choice of hospital does not appear to be preceded by choice of city. In all of the analysis carried out, distance appears to be one of the main influences on a patient's choice of hospital rather than statistics available on the Internet.
2018 5th International Conference on Business and Industrial Research (ICBIR), 2018
The study aims to investigate the appropriate time series techniques for forecasting export value... more The study aims to investigate the appropriate time series techniques for forecasting export values of cars and auto parts (Million Baht). The monthly data are gathered from the website of Ministry of Commerce from January 2010 to December 2017. The data are divided to two datasets. One dataset during January 2010 and December 2016 is consists of 84 observations which is used for build the forecasting model by using Winters' Additive Exponential Smoothing and Box- Jenkins. Another dataset between January 2017 and December 2017 are used for comparing forecast accuracy based on the lowest value of Mean Absolute Deviation (MAD) and Mean Absolute Percent Error (MAPE) and selecting the most appropriate forecasting model. The result shows that Box- Jenkins is the best method for this time series data.
The objectives of this study were to predict the popularity ratings of Thai TV drama programs wit... more The objectives of this study were to predict the popularity ratings of Thai TV drama programs with a prediction model, based on found and synthesized factors affecting them, and to check the accuracy of the model in terms of Root Mean Square Error (RMSE) of the predicted outcomes. The analyzed data were both structured and unstructured data. The structured data included the TV channels airing the programs, type of drama, on-air time, number of episodes, average time per episode, number of viewers watching already aired programs, number of viewers watching the highlight of already aired programs, and number of viewers listening to program soundtracks. The unstructured data included messages posted on Twitter. The messages were processed by sentiment analysis, and the sentiments found were statistically analyzed together with the structured data by multiple regression, yielding predicted popularity ratings. The results show that comments on Thai TV drama programs in social media signi...
The Journal of Applied Science
The research aimed to compare the accuracy of forecasting methods for daily incoming call volume.... more The research aimed to compare the accuracy of forecasting methods for daily incoming call volume. There were three forecasting methods that were used in the study: Box-Jenkins method with SRIMA model and SARIMAX model, Artificial Neural Network (ANN) model and the hybrid model combining SARIMAX and Artificial Neural Network (SARIMAX-ANN) model. The data used in this study is time series of daily incoming call volume to call center which can be divided into 2 data sets. The first data set which was the past data from January 2016 to December 2018 were used for selecting of the most suitable model and the second data set was the past data from January 2019 to December 2019 for the comparison of the accuracy of forecasting model by using Mean Absolute Percentage Error (MAPE). The results showed model with the lowest MAPE is hybrid model of SARIMAX-ANN (MAPE = 24.02%), while the MAPE values for SARIMAX, ANN and SARIMA were 24.06%, 43.70%, and 44.97% respectively. It indicates that the hybrid model is more accurate in forecasting than individual model. The hybrid model can be used to forecast daily incoming call volume which is supporting information for the suitable workforce planning of customer service center in the future.
2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST)
The objectives of this study were the following: (1) to investigate the correlations between data... more The objectives of this study were the following: (1) to investigate the correlations between data collected through Internet of Thing (IOT) and unintentional behavior of drivers (2) to create the models based on machine learning techniques to classify unintentional behavior of drivers who drive the natural gas vehicle and (3) to compare the forecasting accuracy of the learning model. Data studied were collected from the system of the natural gas transportation business in Thailand. There were 10,693 records starting from January 1, 2019 to December 31, 2019, for a period of 12 months. Moreover, KNIME Analytics Platform was used to create the model. The research findings were as follows: (1) duration time when the driver is not looking straight, driving speeds, distance coverage of the driver faces that is not looking straight detecting by a camera and the latitude and longitude coordinates have a relationship with unintentional behavior of the driver; and (2) Neural Network with two hidden layer and 5 neurons in the hidden layer performs the highest accuracy (873%), followed by Support Vector Machine with S3.9%, of accuracy. It can be said that Neural Network can be used to create an efficient predictive model.
The Journal of King Mongkut's University of Technology North Bangkok, 2022
2018 5th International Conference on Business and Industrial Research (ICBIR), 2018
Football is considered one of the most popular sports in Thailand and has high influence on the n... more Football is considered one of the most popular sports in Thailand and has high influence on the nation economy. Thai Premier League is football competition at the top of Thai football league system. The objective of the paper is to evaluate both sportive and financial efficiency of football clubs in Thai Premier League during 2014-2015 football seasons with Data Envelopment Analysis (DEA) model: CCR DEA and super- efficiency DEA. We consider three input factors: the stadium capacity, the capital Investment, the administrative expenses. Nine output variables investigated on the efficiency of football clubs are the number of supportive attendances, the total score in 2015, the total revenues, net assets, the number of trophies, the qualification for AFC for the last and the next season, the qualification for Thai Premier League for the last and the next season. The results show that two football clubs are not efficient. Later, it is found that both football clubs mentioned are relegated to lower league in the next competition 2016/2017. This evidence illustrates that super-efficiency DEA models can be successively to distinguish the efficient clubs and rank the football clubs in Thai Premier League.
When referring to this work, full bibliographic details including the author, title, awarding ins... more When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given e.g.
2021 7th International Conference on Engineering, Applied Sciences and Technology (ICEAST), 2021
We consider a vehicle routing problem starting from a depot to serve customers whose demands are ... more We consider a vehicle routing problem starting from a depot to serve customers whose demands are deterministic using company vehicles. However, the capacities of their own vehicles cannot fulfill all customer demands. Thus, the company must hire vehicles with several vehicle types, each type being defined by a capacity. All company vehicles must return back to the depot, while hiring vehicles do not have to come back to the depot in order to achieve the objective of the minimum total travel distance. This mentioned characteristic of the problem are called Homogeneous Fixed Fleet Close Open Mixed Vehicle Routing Problem (HFFCOMVRP) which is an NP-Hard problem. Therefore, this research presents applying ant colony optimization which is meta-heuristic algorithms for solving complex optimization problems to find good solutions with acceptance in computation time. The algorithm presented is developed in Python and then tested against 15 standard problems of Augerat et al. (1995). The ant colony optimization with improving the solution using 2-Opt and one-move heuristics is efficient in simultaneously determining the open and close routes in the solutions with a wide range of vehicle capacities. It provides the best solution for 12 out of 15 problems
World Academy of Science, Engineering and Technology, International Journal of Mathematical and Computational Sciences, 2016
Decision making on facility locations for blood services and blood distribution plan has an impac... more Decision making on facility locations for blood services and blood distribution plan has an impact on the efficiency of blood supply chain and logistics systems. In the blood supply chain operated by the Thai Red Cross Society (TRCS), problems are faced with amounts of blood collected in different provinces of Thailand being insufficient to meet demand. A proposal has been made to extend this network of blood centres using low-cost collection and distribution centres. Increasing numbers of fixed collection sites can improve access for donors. In addition, some facilities can perform preparation and storage for blood that hospitals can receive directly. Selecting sites for these two types of facility within a limited investment budget informs the strategic plan of this non-profit organisation. Furthermore, we consider the blood delivery problem to hospitals under variable and insufficient supplies of blood. Hospitals are assigned either to fixed routes or variable routes according to...
The objectives of this research were to analyze the relationship of the phrases or words commonly... more The objectives of this research were to analyze the relationship of the phrases or words commonly found in the comments from depression hashtag on Twitter using the association rules. The data used in this study were collected from comments in Thai language via depression hashtag on Twitter during 1 January 2019 to 31 January 2019, in total of 1,500 comments. According to the comments in Thai language on social media collected by using Rapidminer Studio 9 software to get the word about depression and used to analyze relationships of words from a text comment to get the format data Association. The frequency of words and phrases in a form of presentation is used to describe the various opinions about the depression that has a presentation on social media. According to the model performance in each of the above methods, it was found that Euclidean Distance provided the best result due to the smallest average distance at all points in each cluster which was equal to 152.504. The associ...
Proceedings of the 2019 2nd International Conference on Mathematics and Statistics - ICoMS'19, 2019
The objective of this research is to evaluate the relative performance efficiency and determine t... more The objective of this research is to evaluate the relative performance efficiency and determine the factors affecting the efficiency of 11 police stations in the Metropolitan Police Division 3. The first stage is to analyze the efficiency of the police station by Data Envelopment Analysis (DEA) that measures the variable return to scale (VRS) and considering output-orientation. Input variable is the number of police officers. Output variables are the percentage of arrests with remand in custody, from the total amount of arrests, the percentage of arrests with remand in traffic offences, from the total amount of traffic offences, an average score of people's satisfaction on facilities of the police station, operational processes and the service of the staffs. Secondary data are collected from 11 police stations during January and December 2017, for a total of one year. Primary data, which are the satisfaction score, are obtained from the sample survey. For the second stage, the f...
Journal of Physics: Conference Series, 2021
This research objective is to study the latent topics analysis in selling post of real estate of ... more This research objective is to study the latent topics analysis in selling post of real estate of second-hand condominium by using Latent Dirichlet Allocation (LDA) and build a price prediction model of second-hand condominium using multiple linear regression and artificial neural networks by measuring and comparing the performance of the second hand condominium price prediction model with root mean square error (RMSE). This experiment included four variables are room size, number of bathroom, number of bedroom and latent topics from LDA. The result of LDA indicated that selling post of real estate can be separated into 4 topics, in which finding the factors that affect the price use the regression analysis method to get five variables are room size, number of bathroom, floors, topic 2 and topic 4. The RMSE based on the multiple linear regression analysis was 1.349, while the RMSE based on artificial neural network was 1.156. Thus, it can be concluded that the predictive model using ...
Computational Science and Its Applications – ICCSA 2021, 2021
Studies in Computational Intelligence, 2020
The objectives of this research were to analyze the relationship of the phrases or words commonly... more The objectives of this research were to analyze the relationship of the phrases or words commonly found in the comments from depression hashtag on Twitter using the association rules. The data used in this study were collected from comments in Thai language via depression hashtag on Twitter during 1 January 2019 to 31 January 2019, in total of 1,500 comments. According to the comments in Thai language on social media collected by using Rapidminer Studio 9 software to get the word about depression and used to analyze relationships of words from a text comment to get the format data Association. The frequency of words and phrases in a form of presentation is used to describe the various opinions about the depression that has a presentation on social media. According to the model performance in each of the above methods, it was found that Euclidean Distance provided the best result due to the smallest average distance at all points in each cluster which was equal to 152.504. The association analysis, a total of 30 association rules were obtained, the support of 0.5% and the 80% confidence.
Operations Research for Health Care, 2016
Decision making on facility locations for blood services has an impact on the efficiency of suppl... more Decision making on facility locations for blood services has an impact on the efficiency of supply chain and logistics systems. In the blood supply chain operated by the Thai Red Cross Society (TRCS), problems are faced with amounts of blood collected in different provinces of Thailand being insufficient to meet demand. At the present time, TRCS operates one National Blood Centre in the capital and twelve Regional Blood Centres in different provinces to collect, prepare, test, and distribute safe blood. A proposal has been made to extend this network of blood centres using low-cost collection and distribution centres. Increasing numbers of fixed collection sites can improve access for donors. In addition, some facilities will be able to perform preparation and storage for blood that hospitals can receive directly. This paper addresses the selection of sites for two types of facility, either a blood donation room only or donation room with a distribution centre. A range of investment budgets is investigated to inform the strategic plan of this non-profit organisation. We present a novel binary integer programming model for this location-allocation problem based on objectives of improving the supply of blood products while reducing costs of transportation. Computational results are reported, using real life data, that are of practical importance to decision makers.
Health Care Management Science, 2017
As an aid to predicting future hospital admissions, we compare use of the Multinomial Logit and t... more As an aid to predicting future hospital admissions, we compare use of the Multinomial Logit and the Utility Maximising Nested Logit models to describe how patients choose their hospitals. The models are fitted to real data from Derbyshire, United Kingdom, which lists the postcodes of more than 200,000 admissions to six different local hospitals. Both elective and emergency admissions are analysed for this mixed urban/rural area. For characteristics that may affect a patient's choice of hospital, we consider the distance of the patient from the hospital, the number of beds at the hospital and the number of car parking spaces available at the hospital, as well as several statistics publicly available on National Health Service (NHS) websites: an average waiting time, the patient survey score for ward cleanliness, the patient safety score and the inpatient survey score for overall care. The Multinomial Logit model is successfully fitted to the data. Results obtained with the Utility Maximising Nested Logit model show that nesting according to city or town may be invalid for these data; in other words, the choice of hospital does not appear to be preceded by choice of city. In all of the analysis carried out, distance appears to be one of the main influences on a patient's choice of hospital rather than statistics available on the Internet.
2018 5th International Conference on Business and Industrial Research (ICBIR), 2018
The study aims to investigate the appropriate time series techniques for forecasting export value... more The study aims to investigate the appropriate time series techniques for forecasting export values of cars and auto parts (Million Baht). The monthly data are gathered from the website of Ministry of Commerce from January 2010 to December 2017. The data are divided to two datasets. One dataset during January 2010 and December 2016 is consists of 84 observations which is used for build the forecasting model by using Winters' Additive Exponential Smoothing and Box- Jenkins. Another dataset between January 2017 and December 2017 are used for comparing forecast accuracy based on the lowest value of Mean Absolute Deviation (MAD) and Mean Absolute Percent Error (MAPE) and selecting the most appropriate forecasting model. The result shows that Box- Jenkins is the best method for this time series data.
The objectives of this study were to predict the popularity ratings of Thai TV drama programs wit... more The objectives of this study were to predict the popularity ratings of Thai TV drama programs with a prediction model, based on found and synthesized factors affecting them, and to check the accuracy of the model in terms of Root Mean Square Error (RMSE) of the predicted outcomes. The analyzed data were both structured and unstructured data. The structured data included the TV channels airing the programs, type of drama, on-air time, number of episodes, average time per episode, number of viewers watching already aired programs, number of viewers watching the highlight of already aired programs, and number of viewers listening to program soundtracks. The unstructured data included messages posted on Twitter. The messages were processed by sentiment analysis, and the sentiments found were statistically analyzed together with the structured data by multiple regression, yielding predicted popularity ratings. The results show that comments on Thai TV drama programs in social media signi...