Arabic is one of the official languages recognized by the United Nations (UN) and is widely used in the middle east, and parts of Asia, Africa, and other countries. Social media activity currently dominates the textual communication on the Internet and potentially represents people’s views about specific issues. Opinion mining is an important task for understanding public opinion polarity towards an issue. Understanding public opinion leads to better decisions in many fields, such as public services and business. Language background plays a vital role in understanding opinion polarity. Variation is not only due to the vocabulary but also cultural background. The sentence is a time series signal; therefore, sequence gives a significant correlation to the meaning of the text. A recurrent neural network (RNN) is a variant of deep learning where the sequence is considered. Long short-term memory (LSTM) is an implementation of RNN with a particular gate to keep or ignore specific word signals during a sequence of inputs. Text is unstructured data, and it cannot be processed further by a machine unless an algorithm transforms the representation into a readable machine learning format as a vector of numerical values. Transformation algorithms range from the Term Frequency–Inverse Document Frequency (TF-IDF) transform to advanced word embedding. Word embedding methods include GloVe, word2vec, BERT, and fastText. This research experimented with those algorithms to perform vector transformation of the Arabic text dataset. This study implements and compares the GloVe and fastText word embedding algorithms and long short-term memory (LSTM) implemented in single-, double-, and triple-layer architectures. Finally, this research compares their accuracy for opinion mining on an Arabic dataset. It evaluates the proposed algorithm with the ASAD dataset of 55,000 annotated tweets in three classes. The dataset was augmented to achieve equal proportions of positive, negative, and neutral classes. According to the evaluation results, the triple-layer LSTM with fastText word embedding achieved the best testing accuracy, at 90.9%, surpassing all other experimental scenarios.

Deep learning is a machine learning method that gains excellent attention from researchers in recent years. Deep Learning is considered a success in solving various complex problems in the medical image area. For example, brain tumour disease is a deadly disease that causes sufferers to have a low life expectancy after being diagnosed. Diagnosis from experts also takes much time, and experts’ diagnosis results depend on their experience. Therefore, we need an automatic classification that can help experts in making decisions. CNN has been paid much attention to the abilities of complex classification, so there are many state-of-the-art models from the improvement of CNN. Efficient Network is one of CNN models that proposes high accuracy and less computational. Accordingly, this study suggested using the Efficient Network architecture to classify the types of glioma, meningioma, and pituitary brain tumours. Efficient Network has eight levels of category, which are from EfficientNet-B0 to EfficientNet-B7. This study obtains accuracy the best results in EfficientNet-B1 and EfficientNet-B2, which achieved a high accuracy of 96%.

Optimizing a recommender system has complexity and challenging things, such as in collaborative filtering. In collaborative filtering recommendation, the similarities are a critical component. This paper uses predictive KNN to perform Collaborative Filtering, and there have some widespread similarity measurements, such as Euclidean, Minkowski, and generalization from both of them called with Minkowski. We compare them to decide which the best similarity measurement to make better recommendation result by considering the prediction performance and execution time.From the experiment that was performed in this paper, the Minkowski has the best performance but two times slower than Euclidean and Manhattan, since manhattan is trying to find the best p (p=1 or p=2) to decide which p was used. On the other hand, Euclidean performance was approaching the Minkowski, so Euclidean was worth considering.

The study period of the student in a tertiary institution is undoubtedly essential in implementing the objectives of the tertiary institution, particularly for the implementation of the study program, so that its outcomes will affect accreditation. Prediction of students' study period can be a reference for higher education institutions in making policies for the future. Based on XYZ University data, especially in the informatics study program, many students have the different generation and concentration therein. In the implementation of students in studying, several factors, including the value of the Grade Point Average (GPA), can affect the study period taken. Likewise, the institutions often do not understand the conditions or predictive value of students' study period on campus. The application of neural networks in predicting the students’ study period at the XYZ University uses a network model with GPA values as input and 1 layer of hidden layers with 10, 50 and 100 neurons; learning rate values used are 0.01, 0.1 and 0.3 and 1 output target for the study period. Prediction results obtained the best results on the neuron network pattern 50 with 0.01 as a learning rate, which detail of MSE value, the training is 0,017516 and the testing is 0,047721, with an accuracy value of 77%.

Today, consumers are faced with an abundance of information on the internet; accordingly, it is hard for them to reach the vital information they need. One of the reasonable solutions in modern society is implementing information filtering. Some researchers implemented a recommender system as filtering to increase customers’ experience in social media and e-commerce. This research focuses on the combination of two methods in the recommender system, that is, demographic and content-based filtering, commonly it is called hybrid filtering. In this research, item products are collected using the data crawling method from the big three e-commerce in Indonesia (Shopee, Tokopedia, and Bukalapak). This experiment has been implemented in the web application using the Flask framework to generate products’ recommended items. This research employs the IMDb weight rating formula to get the best score lists and TF-IDF with Cosine similarity to create the similarity between products to produce related items.