Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. We introduce the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria—Hausa, Igbo, Nigerian-Pidgin, and Yorùbá—consisting of around 30,000 annotated tweets per language (and 14,000 for Nigerian-Pidgin), including a significant fraction of code-mixed tweets.
With the success of large-scale pre-training and multilingual modeling in Natural Language Processing (NLP), recent years have seen a proliferation of large, web-mined text datasets covering hundreds of languages. We manually audit the quality of 205 language-specific corpora released with five major public datasets (CCAligned, ParaCrawl, WikiMatrix, OSCAR, mC4).
We take a step towards addressing the under representation of the African continent in NLP research by creating the first large publicly available highquality dataset for named entity recognition (NER) in ten African languages, bringing together a variety of stakeholders.
Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. "Low-resourced"-ness is a complex problem going beyond data availability and reflects systemic problems in society.
Sentiment lexicon plays a vital role in lexicon-based sentiment analysis. The lexicon-based method is often preferred because it leads to more explainable answers in comparison with many machine learning-based methods. But, semantic orientation of a word depends on its domain.
With the growing number of literature on movie revenue prediction using machine learning techniques in recent years, a systemic review will help in strengthening the understanding of this research domain. Therefore, this article is aimed at determining the sources of data, the techniques, the features, and the evaluation metrics used in movie revenue prediction.
Viterbi algorithm is a maximum likelihood decoding algorithm. It is used to decode convolutional code in several wireless communication systems, including Wi-Fi. The standard Viterbi algorithm gives just one decoded output, which may be correct or incorrect. Incorrect packets are normally discarded thereby necessitating retransmission and hence resulting in considerable energy loss and delay. Some real-time applications such as Voice over Internet Protocol (VoIP) telephony do not tolerate excessive delay. This makes the conventional Viterbi decoding strategy sub-optimal. In this regard, a modified approach, which involves a form of List Viterbi for decoding the convolutional code is investigated. The technique employed combines the bit-error correction capabilities of both the Viterbi algorithm and the Cyclic Redundancy Check (CRC) procedures. It first uses a form of ‘List Viterbi Algorithm’ (LVA), which generates a list of possible decoded output candidates after the trellis search. The CRC check is then used to determine the presence of correct outcome. Results of experiments conducted using simulation shows considerable improvement in bit-error performance when compared to classical approach.
Timetabling is an essential component of scheduling in all sectors of education. University timetabling entails the scheduling of times and venues for lectures and examinations. These activities are logically structured in a time-wise manner and presented on papers and placed on notice boards in order to avoid conflicts of event. However, timetable schedule forgetfulness, misinterpretation, miscopying, cost of rescheduling and slow time to reach for the rescheduled timetables are the challenges posed by the use of paper and notice board-based timetables; hence, the need for automated timetables. In this paper, we discuss the implementation of Android and web-based timetable customization systems for the Faculty of Computer Science and Information Technology, Bayero University, Kano-Nigeria. The web-based system provides an administrative module that facilitates scheduling and rescheduling of lecture, examination and invigilation timetables. In addition, the Android timetable customization system permits the user to view, customize, set reminders and provide rescheduled timetable updates.
Massive Open Online Course (MOOC) is an emerging learning platform aimed at infinite participation and access through the Internet. Recently, MOOC is globally becoming a key instrument in digitally mediated learning and teaching, due to its ability to provide interactive user forums to support community interactions among participants and instructors. Despite its global acceptance, countries in sub-Saharan Africa suffer some drawbacks within the context of awareness and adoption. Kano state is one of the cities in SubSaharan Africa with high population where MOOCs participation is significantly needed. Therefore, the rationale of this study is to appraise the level of awareness, perceived benefits and challenges of MOOCs adoption among University students of Kano State, Nigeria. The study was conducted in form of a survey using structured questionnaire administered to three hundred (300) randomly selected respondents. Finding from the study revealed a variation in the level of awareness among IT and non IT inclined students. The investigation of MOOC benefits indicates improved learning performance and effectiveness among study samples. The study further revealed user unfriendliness, inadequate Internet connectivity, power instability and cost of enrolments as factors influencing slow adoption of MOOC. The evidence from the study suggests that, awareness and adoption of MOOCs can be enhanced through establishment of hubs, provision of national accredited curriculum and subsidized cost of enrollments.
Cloud computing is fast becoming the major computing paradigm in every aspect of teaching and learning. This computing paradigm supported the emergence of new learning and teaching platform called Massive Open Online Course (MOOC). MOOC is mainly delivered via the cloud and it uses the Internet to make education infinitely available to an unlimited scope of participants. This paper focuses on exploring MOOC as the success of cloud computing in education. A qualitative approach of data collection, selection and analysis were used to systematically review 149 literature for the study. The results of the study showed Infrastructure as a Service (IaaS) and Software as a Service (SaaS) as the major cloud service model used in education. Additionally, Coursera, edX, Udemy, Udacity and FutureLearn are the major MOOC providers using cloud services and resources to globally promote qualitative teaching and learning. Finally, the study outlined the characteristics, types, problems, and prospects of MOOC for education delivery
E-learning systems are increasingly being developed to replace traditional ways of teaching and learning. Studies have shown that technology can be used to create more powerful learning and teaching opportunities over and above traditional systems. Despite these promising technologies of the 21st century, many places of teaching and learning are yet to attain the minimal educational value. In this paper, we proposed a conceptual framework that describes the design and implementation of an ultimate computerized classroom that uses technology to its fullest to enhance educational experience. The framework can likely improve the learning process, enhance students’ performances, and increase students’ interest in education. It can also be used to coordinate and manipulate classroom utilities, manage students’ attendance and educational contents. In addition, the paper described the objectives and implementation considerations for the realization of e-learning full potentials. This is followed by an explanation of the design and implementation details of the three (3) modules that make the system namely; e-register module, e-control module and e-board module. Benefits of the system are explained and the paper review how technology can be incorporated in school education to provide students with the skills needed for the 21st century