UPLB ICS Peak One

Music induces basic to complex emotions such as happiness, sadness, and nostalgia. These emotions can be classified into categories like positive or negative using sentiment analysis. Existing studies on mood classification mostly focus on the audio features of a song while the lyric features are ignored. A few studies on lyrics mood classification, on the other hand, pointed out the need to explore other classifiers like Naı̈ve Bayes and improve its performance, using a larger dataset. In this study, a Naı̈ve Bayes classifier model was created to identify whether a song is positive or negative based on its lyrics. The model which produced exceptional results with 95.02% accuracy and 94.42% precision was trained and tested using a dataset containing 1,810 song lyrics. Feature extraction techniques such as N-grams (trigrams) and TF-IDF were applied after preprocessing the data.

Traditional Meter Reading where a meter man does an ocular visit to each household to log the water consumption indicated in the water meters is very time-consuming and inefficient. This study proposes a new system that revolves around a mounted meter reading device with Wi-Fi connectivity as its main way to communicate with the server. This comes along with a new information system that has features based on the existing application used by the Client. To showcase automation, a digit recognition script was used to identify the digits indicated in the water meter through Neural Network. The client, Molino Homes Water Management, evaluated the proposed system, its features and plausibility of the system to replace their current system through a Client Satisfaction Survey. The results were non-satisfactory as the system was deemed to be average and currently cannot be deployed. Nonetheless, the clients are still interested for the system once it is industry grade and scalable to the whole subdivision.

The rise of social media has led to the widespread use of online posts as valuable data for machine learning studies. However, these studies often encounter the challenge of dealing with metaphors embedded in the text, which can introduce inconsistencies in data processing since metaphors are known to change meaning of text. This challenge is even more prominent in high context languages such as Filipino. In response to this issue, multiple novelties were introduced in this study. These novelties are the Filipino metaphor corpus, the Filipino metaphor identifier created that utilizes an automatic definition selector, and finally a modified metaphor counting method in the evaluation.

SalesPal is a mobile application designed to provide a centralized management platform to sellers who have online business on different e-commerce platforms. This study presents the development, implementation, and evaluation of SalesPal as a solution to the need of managing multiple online businesses. The usability of the application was evaluated by using the System Usability Scale (SUS) questionnaire, which yielded an average SUS score of 81.5 obtained from sellers, indicating a favorable level of usability.

The Philippines’ Inter-Agency Task Force for the Management of Emerging Infectious Diseases established protocols in accordance with the World Health Organization’s guidelines to prevent the spread of COVID-19. Most prominent of these are the different alert levels which mandated the wearing of face masks and face shields, and complying with social distancing. The study used Haar-cascade Classifiers and AdaBoost to create a program that can detect the presence of faces from a webcam video feed. The program trained three classifier models each with their own 24x24 detector window to classify faces that are not wearing a mask, wearing a mask, and wearing a shield. Performance analysis showed that the program can detect the three classifications but can also misidentify non-face objects, with the face, mask, and shield classifiers getting F1 scores of 0.64, 0.7, and 0.83 respectively, suggesting that the data sets used to train the models can be further improved.