Our work focuses on detecting sarcasm in tweets using deep learning extracted features combined with contextual handcrafted features. A feature set is extracted from a Convolutional Neural Network (CNN) architecture before it is combined with carefully handcrafted feature sets. These handcrafted feature sets are created based on their respective contextual explanations. Each feature sets are specifically designed for the sole task of sarcasm detection. The objective is to find the most optimal features. Some sets are good to go even when it is used in independence. Other sets are not really significant without any combination. The results of the experiments are positive in terms of Accuracy, Precision, Recall and F1-measure. The combination of features are classified using a few machine learning techniques for comparison purposes. Logistic Regression is found to be the best classification algorithm for this task. Furthermore, result comparison to recent works and the performance of each feature set are also shown as additional information.

The concept of mobile Virtual Reality (VR) headset that utilize mobile smartphone as the main display and processing device has successfully achieved a low-cost but yet feasible method to implement VR for a mobile user. However, locomotion in mobile VR is still a challenge because the ways to interact with the smartphone are limited. Walking-in-place (WIP) can be used as a hands-free input method to control locomotion inside a mobile VR environment, at the same time, enhance user experience by increasing the sense of immersion. Commonly, WIP implementation in mobile VR uses the inertia sensors of smartphone to detect WIP, thus no additional apparatus is needed. However, common WIP implementation navigates based on user’s gaze direction, but in reality, we may walk and look into different direction at the same time. Besides that, fatigue caused by WIP is another important issue to be considered for prolongs usage of VR application. So, we present a less fatigue WIP gesture, swing-in-place (SIP) with a WIP implementation that allows users to travel and look in different directions during locomotion. Our implementation used only the accelerometer and gyroscope in single smartphone. Evaluation results show that SIP able to provide a similar feeling of immersion and it is less fatigue when compared with a common WIP method used in mobile VR. The side-viewing functionality is liked by the users.

In recent years, hand-tracking technologies had been implemented in Virtual Reality application, allowing users to use natural hand gesture for interaction within the environment. However, little efforts have been conducted in understanding user's preference when they use their hands to interact with the VR world. In this paper, the result of a guessability test for hand gestures in order to operate musical tasks to support music interaction within immersive Virtual Environment. A total number of 750 gestures have been elicited from 15 participants for 50 selected tasks, including 10 musical tasks. Our result enables a smaller size of gesture set to be elicited from the users. The implications of this work can be relevant in hand gesture design, gesture interaction, and gestural interfaces design for music interaction, all of which are highlighted in this study.

Sentiment analysis is the computational study of opinions given by the users of online media platforms e.g. Twitter, Facebook, Instagram. The output will be in the form of polarity: positive, negative or indifferent. The field has become very useful for the industry as it can feed them the information of what is sought after by their customers in a given time. It has also rapidly became a topic of interest in the research world, for its importance and subjectivity. One of the most challenging issue in sentiment analysis is sarcasm. The existence of sarcasm is mostly ignored by the researchers in the field of sentiment analysis as it is considered to be too complex. Sarcasm is what most researchers regarded as a subset of irony. It is the utterance of positive statement with negative intent. Intent is hard to detect not only for computers but also for humans. The listener is deemed to have a certain degree of background knowledge or context of what the speaker is saying to understand sarcasm. The researches that takes sarcasm into account or solely focuses on sarcasm is in the trend of using context outside the target word for sarcasm detection, and the most popular approach is deep learning. However, both deep learning and context need a lot of features. In this paper, we will look at some researches that focuses on sarcasm detection and their agreement that more than text is needed to properly detect sarcasm. Also in this paper is the trends undergone by sarcasm detection researchers and their proposed techniques.

Due to the recent COVID-19 pandemic that has swept the globe, more people are working from home. People use synchronous applications to communicate remotely because they are not able to meet face-to-face. However, few research studies on the issues surrounding the virtual conference application, particularly those that include collaborative activities, have been conducted. The usability study recruited 16 participants (in four groups of four) to communicate synchronously while performing collaborative activities, such as drawing together on a shared screen. According to the findings of the usability study, users do not often use the collaborative tools provided by the current virtual conference application. This is due to low exposure and unfamiliarity with the use of collaborative tools. The findings also show that users frequently do not turn on the web camera due to several reasons, including privacy, connectivity issues, the environment, and background distraction. Turning on the web camera can also cause anxiety due to shyness in front of the camera. However, some participants prefer to turn on the web camera so that they can see each other’s reactions when performing collaborative activities. The article provides several guidelines to assist in the design of virtual conference applications, including a simple familiar intuitive interface to encourage the use of collaborative tools and also introduces the use of virtual avatars as a way to represent oneself during online meetings to allow affective sharing while respecting the privacy of its users.

This work discuss the task of automatically detecting satire instances in short articles. It is the study of extracting the most optimal features by using a deep learning architecture combined with carefully handcrafted contextual features. It is found that a few sets can perform well when they are used independently, but the others not so much. However, even the latter sets become very useful after the combination process with the former sets. This shows that each of the feature sets are significant. Finally, the combined feature sets undergoes the classification using well-known machine learning classification algorithms. The best algorithm for this task is found to be Logistic Regression. The outcome of all the experiments are good in all the metrics used. The result comparison to existing works in the same domain shows that the proposed method is slightly better with 0.94 in terms of F1-measure, while existing works managed to obtain 0.91 (Yang et al. , 2017), 0.90 (Zhang et al. , 2016), and 0.88 (Rubin et al. , 2016). The performance of each feature sets are also given as additional information. The main purpose of this work is to show that the combination of features extracted using supervised learning with the ones extracted manually can yield a good performance. It is also to open doors for other researchers to take into account the contextual meaning behind a figurative language type such as satire.