Mohammad Al-Smadi

SemEval-2016 task 5 : aspect based sentiment analysis

This paper describes the SemEval 2016 shared task on Aspect Based Sentiment Analysis (ABSA), a continuation of the respective tasks of 2014 and 2015. In its third year, the task provided 19 training and 20 testing datasets for 8 languages and 7 domains, as well as a common evaluation procedure. From these datasets, 25 were for sentence-level and 14 for text-level ABSA; the latter was introduced for the first time as a subtask in SemEval. The task attracted 245 submissions from 29 teams.

Human Annotated Arabic Dataset of Book Reviews for Aspect Based Sentiment Analysis

With the prominent advances in Web interaction and the enormous growth in user-generated content, sentiment analysis has gained more interest in commercial and academic purposes. Recently, sentiment analysis of Arabic user-generated content is increasingly viewed as an important research field. However, the majority of available approaches target the overall polarity of the text. To the best of our knowledge, there is no available research on aspect-based sentiment analysis (ABSA) of Arabic text. This can be explained due to the lack of publically available datasets prepared for ABSA, and to the slow progress in sentiment analysis of Arabic text research in general. This paper fosters the domain of Arabic ABSA, and provides a benchmark human annotated Arabic dataset (HAAD). HAAD consists of books reviews in Arabic which have been annotated by humans with aspect terms and their polarities. Nevertheless, the paper reports a baseline results and a common evaluation technique to facilitate future evaluation of research and methods.

Enhancing the determination of aspect categories and their polarities in Arabic reviews using lexicon-based approaches

Sentiment Analysis (SA) is the process of determining the sentiment of a text written in a natural language to be positive, negative or neutral. It is one of the most interesting subfields of natural language processing (NLP) and Web mining due to its diverse applications and the challenges associated with applying it on the massive amounts of textual data available online (especially, on social networks). Most of the current works on SA focus on the English language and work on the sentence-level or the document-level. This work focuses on the less studied version of SA, which is aspect-based SA (ABSA) for the Arabic language. Specifically, this work considers two ABSA tasks: aspect category determination and aspect category polarity determination, and makes use of the publicly available human annotated Arabic dataset (HAAD) along with its baseline experiments conducted by HAAD providers. In this work, several lexicon-based approaches are presented for the two tasks at hand and show that some of the presented approaches significantly outperforms the best known result on the given dataset.

Scaling Informal Learning at the Workplace: A Model and Four Designs from a Large-Scale Design-Based Research Effort.

Workplace learning happens in the process and context of work, is multi-episodic, often informal, problem based and takes place on a just-in-time basis. While this is a very effective means of delivery, it also does not scale very well beyond the immediate context. We review three types of technologies that have been suggested to scale learning and three connected theoretical discourses around learning and its support. Based on these three strands and an in-depth contextual inquiry into two workplace learning domains, health care and building and construction, four design-based research projects were conducted that have given rise to designs for scaling informal learning with technology. The insights gained from the design and contextual inquiry contributed to a model that provides an integrative view on three informal learning processes at work and how they can be supported with technology: (1) task performance, reflection and sensemaking; (2) help seeking, guidance and support; and (3) emergence and maturing of collective knowledge. The model fosters our understanding of how informal learning can be scaled and how an orchestrated set of technologies can support this process.

Using big data analytics for authorship authentication of arabic tweets

Authorship authentication of a certain text is concerned with correctly attributing it to its author based on its contents. It is a very important problem with deep root in history as many classical texts have doubtful attributions. The information age and ubiquitous use of the Internet is further complicating this problem and adding more dimensions to it. We are interested in the modern version of this problem where the text whose authorship needs authentication is an online text found in online social networks. Specifically, we are interested in the authorship authentication of tweets. This is not the only challenging aspect we consider here. Another challenging aspect is the language of the tweets. Most current works and existing tools support English. We chose to focus on the very important, yet largely understudied, Arabic language. Finally, we add another challenging aspect to the problem at hand by addressing it at a very large scale. We present our effort to employ big data analytics to address the authorship authentication problem of Arabic tweets. We start by crawling a dataset of more than 53K tweets distributed across 20 authors. We then use preprocessing steps to clean the data and prepare it for analysis. The next step is to compute the feature vectors of each tweet. We use the Bag-Of-Words (BOW) approach and compute the weights using the Term Frequency-Inverse Document Frequency (TF-IDF). Then, we feed the dataset to a Naive Bayes classifier implemented on a parallel and distributed computing framework known as Hadoop. To the best of our knowledge, none of the previous works on authorship authentication of Arabic text addressed the unique challenges associated with (1) tweets and (2) large-scale datasets. This makes our work unique on many levels. The results show that the testing accuracy is not very high (61.6%), which is expected in the very challenging setting that we consider.

SOA-based architecture for a generic and flexible e-assessment system

In the last decade, universities and higher education institutes have become more and more interested in using computers to deliver their formative and summative assessments. Therefore, several computer-assisted-assessment systems have been developed. The variance in the application domains of e-assessment has a main influence on having different assessment systems in the same university. Since universities have different colleges and specializations based on their types and in order to deliver their assessment activities online, each college is developing or buying assessment system or tools based on its specializations and courses. This has caused some universities to have more than one computer-assisted-assessment system. In this paper, a service-oriented e-assessment system will be suggested to solve this problem. A service-oriented architecture for a generic and flexible assessment system will be provided with cross-domain use cases to show the flexibility of this architecture.

Paraphrase identification and semantic text similarity analysis in Arabic news tweets using lexical, syntactic, and semantic features

The rapid growth in digital information has raised considerable challenges in particular when it comes to automated content analysis. Social media such as twitter share a lot of its users information about their events, opinions, personalities, etc. Paraphrase Identification (PI) is concerned with recognizing whether two texts have the same/similar meaning, whereas the Semantic Text Similarity (STS) is concerned with the degree of that similarity. This research proposes a state-of-the-art approach for paraphrase identification and semantic text similarity analysis in Arabic news tweets. The approach adopts several phases of text processing, features extraction and text classification. Lexical, syntactic, and semantic features are extracted to overcome the weakness and limitations of the current technologies in solving these tasks for the Arabic language. Maximum Entropy (MaxEnt) and Support Vector Regression (SVR) classifiers are trained using these features and are evaluated using a dataset prepared for this research. The experimentation results show that the approach achieves good results in comparison to the baseline results.

Supporting self-regulated learners with formative assessments using automatically created QTI-questions

Recently, a new age of information has appeared where information and communication technology plays a major role in education and learning society. Consequently, modern learning settings represented by emerging learning strategies have been used in higher education. A primary goal for higher education is to support students and lifelong learners to be independent, self-motivated, and self-regulated. As a result, students should be provided with enhanced approaches of learning and assessment that support them to set their learning goals effectively, to plan and use effective strategies in order to achieve their goals, to manage resources, to monitor their understanding, and to assess their progress towards their goals. This paper proposes an enhanced approach of e-assessment where automatically created formative assessments are provided to support self-regulated learners.

Service-oriented flexible and interoperable assessment: towards a standardised e-assessment system

Free-text answers assessment has been a field of interest during the last 50 years. Several free-text answers assessment tools underpinned by different techniques have been developed. In most cases, the complexity of the underpinned techniques has caused those tools to be designed and developed as stand-alone tools. The rationales behind using computers to assist learning assessment are mainly to save time and cost, as well as to reduce staff workload. However, utilising free-text answers assessment tools separately form the learning environment may increase the staff workload and increase the complexity of the assessment process. Therefore, free-text answers scorers have to have a flexible design to be integrated within the context of the e-assessment system architectures taking advantages of software-as-a-service architecture. Moreover, flexible and interoperable e-assessment architecture has to be utilised in order to facilitate this integration. This paper discusses the importance of flexible and inte...

Modular Assessment System for Modern Learning Settings: MASS

In the last three decades, the field of e-assessment has become more important. Several universities and higher education institutes have started to provide online assessments. The variance in the e-assessment application domains as well as the market competition has caused several e-assessment systems to be developed. As the universities cover different subjects and courses, they may have more than one e-assessment system based on the department and the course. Therefore, more resources and budgeting planes are required. This paper discusses the possibility of a generic and flexible e-assessment system as a way to solve this problem. Furthermore, it investigates the generality and flexibility requirements in the field of e-assessment and provides appropriate architecture for a modular assessment system with reference to these requirements.