Ontology-Enabled Emotional Sentiment Analysis on COVID-19 Pandemic-Related Twitter Streams

The exponential growth of social media users has changed the dynamics of retrieving the potential information from user-generated content and transformed the paradigm of information-retrieval mechanism with the novel developments on the concept of “web of data”. In this regard, our proposed Ontology-Based Sentiment Analysis provides two novel approaches: First, the emotion extraction on tweets related to COVID-19 is carried out by a well-formed taxonomy that comprises possible emotional concepts with fine-grained properties and polarized values. Second, the potential entities present in the tweet can be analyzed for semantic associativity. The extraction of emotions can be performed in two cases: (i) words directly associated with the emotional concepts present in the taxonomy and (ii) words indirectly present in the emotional concepts. Though the latter case is very challenging in processing the tweets to find the hidden patterns and extract the meaningful facts associated with it, our proposed work is able to extract and detect almost 81% of true positives and considerably able to detect the false negatives. Finally, the proposed approach's superior performance is witnessed from its comparison with other peer-level approaches.

A Platform for Keyword Search and its Application for COVID-19 Pandemic Data

Keyword search is typically associated with information retrieval systems. However, recently, keyword search has been expanded to relational databases and RDF datasets, as an attractive alternative to traditional database access. This paper introduces DANKE, a platform for keyword search over databases, and discusses how third-party applications can be equipped with DANKE to take advantage of a data retrieval mechanism that does not require users to have specific technical skills for searching, retrieving and exploring data. The paper ends with the description of an application, called CovidKeyS, which uses DANKE to implement keyword search over three COVID-19 data scenarios.

Using Wikipedia's Big Data for creation of Knowledge Bases

Wikipedia is among the most prominent and comprehensive sources of information available on the WWW. However, its unstructured form impedes direct interpretation by machines. Knowledge Base (KB) creation is a line of research that enables interpretation of Wikipedia's concealed knowledge by machines. In light of the efficacy of KBs for the storage and efficient retrieval of semantic information required for powering several IT applications such Question-Answering System, many large-scale knowledge bases have been developed. These KBs have employed different approaches for data curation and storage. The retrieval mechanism facilitated by these KBs is also different. Further, they differ in their depth and breadth of knowledge. This paper endeavours to explicate the process of KB creation using Wikipedia and compare the prominent KBs developed using the big data of Wikipedia.

Tubular microdomains of Rab7-endosomes retrieve TrkA, a mechanism disrupted in Charcot-Marie-Tooth 2B

Axonal survival and growth requires signalling from tropomyosin receptor kinases (Trks). To transmit their signals, receptor-ligand complexes are endocytosed and retrogradely trafficked to the soma where downstream signalling occurs. Vesicles transporting neurotrophic receptors to the soma are reported to be Rab7-positive late endosomes/multi vesicular bodies where receptors localize within so-called intraluminal vesicles. Therefore, one challenging question is how downstream signalling is possible given the insulating properties of intraluminal vesicles. In this study, we report that Rab7-endosomes/multi vesicular bodies retrieve TrkA through tubular microdomains. Interestingly, this phenotype is absent for the EGF-receptor. Further, we found that EndophilinA1, EndophilinA2 and EndophilinA3 together with WASH1 are involved in the tubulation process. In Charcot-Marie-Tooth 2B, a neuropathy of the peripheral nervous system, this tubulating mechanism is disrupted. In addition, the ability to tubulate correlates with the phosphorylation levels of TrkA as well as with neurite length in neuronal cultures from dorsal root ganglia. In all, we report a new retrieval mechanism of late Rab7-endosomes, which enables TrkA signalling and sheds new light onto how neurotrophic signalling is disrupted in CMT2B.

Modeling Sentence Comprehension Deficits in Aphasia: A Computational Evaluation of the Direct-Access Model of Retrieval

Several researchers have argued that sentence comprehension is mediated via a content addressable retrieval mechanism that allows fast and direct access to memory items. Initially failed retrievals can result in backtracking, which leads to correct retrieval. We present an augmented version of the direct access model that allows backtracking to fail. Based on self-paced listening data from individuals with aphasia, we compare the augmented model to the base model without backtracking failures. The augmented model shows quantitatively similar performance to the base model, but only the augmented model can account for slow incorrect responses. We argue that the modified direct-access model is theoretically better suited to fit data from impaired populations.

Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation

Transformer-based models have demonstrated excellent capabilities of capturing patterns and structures in natural language generation and achieved state-of-the-art results in many tasks. In this paper we present a transformer-based model for multi-turn dialog response generation. Our solution is based on a hybrid approach which augments a transformer-based generative model with a novel retrieval mechanism, which leverages the memorized information in the training data via k-Nearest Neighbor search. Our system is evaluated on two datasets made by customer/assistant dialogs: the Taskmaster-1, released by Google and holding high quality, goal-oriented conversational data and a proprietary dataset collected from a real customer service call center. Both achieve better BLEU scores over strong baselines.

A STUDY OF STATUS OF RETRIEVAL MECHANISM FOR PATIENTS TAKING ANTITUBERCULAR TREATMENT UNDER NTEP

Introduction--A observational study was conducted in the Department Of Respiratory Medicine in a tertiary care centre who were taking ATT under DOTS or had history of ATTconsumption in the past. Aim :Aim of the study was to evaluate the status of a retrieval mechanism for patients who are lost to follow-up and to identify the strengths and weakness in the dispersal of medications, monitoring and follow-up of patients and status of retrieval mechanism. Materials and Methods: The study was carried out among 201 patients coming to the Department of Respiratory Medicine who were on ATTunder DOTS or had received ATTin the past. Demographic details and clinical ndings were noted. Data collected was entered into Excel spread sheet and quantitative data were expressed as number and percentage. Results- Among 201 participants 17.4% missed their doses whereas 82.6% of the participants took their medications regularly. Among the patients who missed their doses retrieval actions were taken in only 42.9%participants.Among those participants in whom retrieval actions were taken 14.3% were lost to follow up,97.14 % of the participants who missed their doses received multiple days medications. Besides this, 80% of the participants who missed their doses suffered from adverse effects of ATTduring their course of treatment. Conclusion—From this study we conclude that under NTEPmajority of patients are taking ATT regularly but regular follow-up of patients on ATT and retrieval action is not upto the mark and it should be strengthened to prevent development of DRTB and its spread in the community.

A cross-linguistic investigation of proactive, similarity-based retrieval interference in sentence comprehension: No support from English, German and Russian eye-tracking data

Cue-based parsing theories posit that dependency resolution during real-time sentence comprehension relies on cue-based retrieval of linguistic items encoded in memory. This retrieval mechanism is prone to similarity-based interference, which can occur when there are items in memory that are similar to the retrieval target. Interference during sentence comprehension seems to be well-established across numerous syntactic dependencies; however, the evidence for interference on within-sentence dependencies from sentence-external lexical items (encoded in memory prior to reading a target dependency) is inconclusive (Van Dyke &McElree, 2006; Van Dyke et al., 2014). The goal of the present study is to provide a large-scale cross-linguistic investigation of retrieval interference from sentence-external distractors under varying processing demands. Three larger-sample eye-tracking studies in English (N=66),German (N=122) and Russian (N=109) show no support for similarity-based interference from sentence-external material during sentence comprehension. We discuss the implications of our findings for cue-based parsing theories.

The Role of Prior Event Retrieval in Encoding Changed Event Features

When people experience everyday activities, their comprehension can be shaped by expectations that derive from similar recent experiences, which can affect the encoding of the new experience into memory. When a new experience includes changes—such as a driving route being blocked by construction—this can lead to interference in subsequent memory. However, theories based on prediction-error-driven learning propose that unpredicted changes can lead to facilitation rather than interference. One potential mechanism of effective encoding of event changes is the retrieval of related features from previous events. Another such mechanism is the generation of a prediction error when a predicted feature is contradicted. In two experiments, we tested for effects of these two mechanisms on memory for changed features in movies of everyday activities. Participants viewed movies of an actor performing everyday activities across two fictitious days. Some event features changed across the days, and some features violated viewers’ predictions. Retrieval of previous event features while viewing the second movie was associated with better subsequent memory, providing evidence for the retrieval mechanism. Contrary to our hypotheses, there was not support for the error mechanism: Prediction error was not associated with better memory when it was observed correlationally (Experiment 1) or directly manipulated (Experiment 2). These results support a key role for episodic retrieval in the encoding of new events. They also indicate boundary conditions on the role of prediction errors in driving new learning. Both findings have clear implications for theories of event memory.

An ontology-based information retrieval mechanism for E-learning management system

During the last decade, increasing attention has been focused on ontologies and Ontological Engineering. The application of ontological engineering technique to e-learning, though still in its early stage, has become a phenomena tool in the integration and adaptation of a dynamic and flexible elearning environment, where tutors and learners are provided with the functionality of personalizing their learning process, this has not fully considered the generality of an entire field of study. This paper presents an ontology-based framework for classification of the entire courses of computer science at the university level. A model of an e-learning domain in the context of material classification that enables students retrieve information about a particular course in personalized ways was presented the method adopted elicited e-learning knowledge using documented materials, observation, consultation, prototyping among others. With domain expertise developed, the knowledge elicited was analyzed and formally represented using OWL-Description Logic. The design was implemented using Protégé 5.0 editor. The validation for accuracy and completeness was carried out with the domain and ontology experts using consistency checking reasoned, DL-Query. The results of the implementation show that elearning materials can be searched and retrieved easily and timely. The study also established and formalised an effective computational approach for representing information content of educational resources thereby helping to improve the flexibility of content representation in an e-learning system.Keywords: e-learning, Ontological Engineering, Ontology, Ontology Web Language (OWL), Knowledge Management, Description LogicVol. 26, No 1, June 2019