Once a Journalist, Always a Journalist: A Digital Ethnography of a Facebook COVID Microsite

The task of named entity recognition (NER) is to identify and classify words and phrases denoting named entities, such as people, organizations, geographical names, dates, events, terms from subject areas. While searching for the best solution, researchers conduct a wide range of experiments with different technologies and input data. Comparison of the results of these experiments shows a significant discrepancy in the quality of NER and poses the problem of determining the conditions and limitations for the application of the used technologies, as well as finding new solutions. An important part in answering these questions is the systematization and analysis of current research and the publication of relevant reviews. In the field of named entity recognition, the authors of analytical articles primarily consider mathematical methods of identification and classification and do not pay attention to the specifics of the problem itself. In this survey, the field of named entity recognition is considered from the point of view of individual task categories. The authors identified five categories: the classical task of NER, NER subtasks, NER in social media, NER in domain, NER in natural language processing (NLP) tasks. For each category the authors discuss the quality of the solution, features of the methods, problems, and limitations. Information about current scientific works of each category is given in the form of a table for clarity. The review allows us to draw a number of conclusions. Deep learning methods are leading among state-of-the-art technologies. The main problems are the lack of datasets in open access, high requirements for computing resources, the lack of error analysis. A promising area of research in NER is the development of methods based on unsupervised techniques or rule-base learning. Intensively developing language models in existing NLP tools can serve as a possible basis for text preprocessing for NER methods. The article ends with a description and results of experiments with NER tools for Russian-language texts.

Named entity recognition (NER) seeks to identify and classify named entities within bodies of text into language categories such as nouns, that are reflective of locations, organizations, and people. As it is language dependent, the approach taken for most NER systems are domain-general, meaning that they are designed based on a language and not on a specific targeted domain. With current usage of non-formal languages on social media, this instigates the need to compare the performance of domain-general and domain specific NERs. A domain specific NER (vehicle traffic domain), TEXT, is described and the performance of domain-general NER versus TEXT is compared. The results of the evaluation show that the performance of domain-specific NER significantly outperforms domain-general NER. The domain-general NER could only perform adequately for common scenarios.

The medical security privacy and named entity recognition (NER) technology under the blockchain technology has been a hot topic in all walks of life. As a typical representative of medical security risks and NER, the NER model of online social media based on active learning has attracted worldwide attention. NER is an important part of natural language processing. Traditional recognition technology usually requires a lot of external information, and through the manual identification of its features, which costs a lot of time and energy. In order to solve the shortcomings of traditional recognition algorithms and the lack of feature extraction in network media NER, a new active learning model was introduced in this paper. In the information age, people are increasingly demanding a large amount of text information, and NER technology came into being. Its main function is to accurately identify important information from text and provide useful information for high-level work. The initial design of NER system is mainly based on the recognition of rules, so as to realize the recognition of named entities. However, in a complex network environment, it takes a lot of time and energy to establish rules without conflicts, and it has poor mobility. In recent years, with the continuous development of computer technology, the use of machine learning to actively learn the unknown information in the target area reduces the workload of manual annotation, thus realizing the active learning of large amounts of data. The research showed that the recognition accuracy under the traditional NER was low, and the information processing speed was slow; the accuracy rate of NER based on active learning was as high as 97%, and the speed of information processing had also been greatly improved, which had solved many problems under the traditional mode. User satisfaction could be as high as 95%, which showed that the latter had broad prospects. The progress of the new era cannot be separated from the support of new technologies. The research of this article has important guiding significance for medical security privacy and the application of NER under blockchain technology.

Named entity recognition (NER) is a subfield of natural language processing (NLP). It is able to identify proper nouns, such as person names, locations, and organizations, and has been widely used in various tasks. NER can be practical in extracting information from social media data. However, the unstructured and noisy nature of social media (such as grammatical errors and typos) causes new challenges for NER, especially for low-resource languages such as Persian, and existing NER methods mainly focus on formal texts and English social media. To overcome this challenge, we consider Persian NER as an optimization problem and use the binary Gray Wolf Optimization (GWO) algorithm to segment posts into small possible phrases of named entities. Later, named entities are recognized based on their score. Also, we prove that even human opinion can differ in the NER task and compare our method with other systems with the S e p _ T D _ T e l 01 dataset and the results show that our proposed system obtains a higher F1 score in comparison with other methods.

Named Entity Recognition (NER) is gaining popularity in multiple Information Retrieval applications as it facilitates information extraction. Main goal of NER is to obtain named entities which are usually proper nouns, temporal entities and numerical values. Initial Named Entity Recognizers were designed to deal with formal English text. With increased use of social media, many IR and Natural Language Processing based applications designed to get information from short text like tweets. Formal text based standard NER systems fail to deal with such short text due to limited information and presence of noise. Ample work has been done for NER systems which handle English short text. Relatively Indian languages, especially Marathi, need to build dedicated NER systems to extract named entities from tweets. From multiple approaches of NER, a Conditional Random Fields (CRFs) has shown good accuracy for some Indian languages like Hindi. So here we have proposed a dedicated NER system with CRF based hybrid approach to identify NEs from Marathi tweets. Multiple linguistic features are used in addition to Marathi gazetteers to facilitate the task.

Many research problems involving medical texts have limited amounts of annotated data available (e.g., expressions of rare diseases). Traditional supervised machine learning algorithms, particularly those based on deep neural networks, require large volumes of annotated data, and they underperform when only small amounts of labeled data are available. Few-shot learning (FSL) is a category of machine learning models that are designed with the intent of solving problems that have small annotated datasets available. However, there is no current study that compares the performances of FSL models with traditional models (e.g., conditional random fields) for medical text at different training set sizes. In this paper, we attempted to fill this gap in research by comparing multiple FSL models with traditional models for the task of named entity recognition (NER) from medical texts. Using five health-related annotated NER datasets, we benchmarked three traditional NER models based on BERT-BERT-Linear Classifier (BLC), BERT-CRF (BC) and SANER; and three FSL NER models-StructShot & NNShot, Few-Shot Slot Tagging (FS-ST) and ProtoNER. Our benchmarking results show that almost all models, whether traditional or FSL, achieve significantly lower performances compared to the state-of-the-art with small amounts of training data. For the NER experiments we executed, the F1-scores were very low with small training sets, typically below 30%. FSL models that were reported to perform well on non-medical texts significantly underperformed, compared to their reported best, on medical texts. Our experiments also suggest that FSL methods tend to perform worse on data sets from noisy sources of medical texts, such as social media (which includes misspellings and colloquial expressions), compared to less noisy sources such as medical literature. Our experiments demonstrate that the current state-of-the-art FSL systems are not yet suitable for effective NER in medical natural language processing tasks, and further research needs to be carried out to improve their performances. Creation of specialized, standardized datasets replicating real-world scenarios may help to move this category of methods forward.

Named Entity Recognition (NER) is a task of extracting entities such as person, location, and organization from texts. NER is more challenging in the social media texts compared to the formal texts due to the noisy language including grammatical errors and abbreviations. However, the problem of NER in the social media gained significant attention in the literature due to the amount of information flow in the social media. In this paper, we propose a comprehensive model for NER in Turkish texts of distinct social media domains, i.e. Twitter, Facebook, and Donanimhaber Forum. The model employs Conditional Random Fields followed by Bidirectional Long Short Term Memory. To overcome the challenges of social media texts, we incorporate word embeddings, character representations, morphology, domain information, pattern-matching, dictionary, part-of-speech, and casing based features to our model. We perform ablation studies to analyze the effect of these features. We demonstrate the success of our model for tagging Turkish social media texts through the largest Turkish NER database.

Recruiting future talent in ecology and evolutionary biology

The application of Natural Language Processing (NLP) tasks to the attractive social media corpus is very challenging because social media users often prefer communicating with casual language using out- of-vocabulary (OOV) words and internet abbreviations (Slang). That's why, we have to boost the performance of NLP tasks when applied to social media text. So, we are interested in improving the very major fundamental NLP task, Named Entity Recognition (NER), which assign to each entity a label whether it's a (person, location, organization, etc.) from Twitter. NER will be improved by converting non-standard entities to their canonical form called the Named Entity Normalization (NEN). In this paper, we propose a novel weakly supervised joint approach for named entity recognition and normalization for noisy text. We jointly conduct weakly supervised NER and normalization of both single-token OOV words and multitoken Slang to recognize and restore any type of named entities to their canonical form. This approach can give better results than existing state-of-art NER systems, NEN systems and pipe line approaches.

Data mining provides a wealth of actionable intelligence for enhancing internet-based, query-based AI. This study focuses on the importance of Named Entity Recognition (NER) in extracting valuable information from social media's dynamic and extensive realm. This research paper introduces a novel method for performing Named Entity Recognition in a distributed setting, specifically designed to address the unique difficulties presented by social media data. This research investigates the effectiveness of combining Bidirectional Long Short-Term Memory (Bi-LSTM) and Maximum Entropy Markov Model (MEMM) as Bi-MEMM for improving Named Entity Recognition (NER) accuracy. This research presents a model that uses Bi-LSTM to effectively capture the bidirectional context in social media text. By leveraging this approach, the model can accurately identify complex named entities within the text. This study utilises the Maximum Entropy Markov Model (MEMM) to effectively capture and model the dependencies between labels, thereby enhancing the accuracy and precision of entity recognition. This study focuses on the significance of a distributed environment in the context of social media, where data is generated rapidly. This research presents a system optimising performance by leveraging distributed computing resources for parallel processing. This study examines the performance evaluations of a model in identifying named entities in user-generated content across diverse datasets. The findings demonstrate the model’s effectiveness in this task with an accuracy of 99.3%. This research focuses on developing a system that operates in a distributed environment to ensure precision and efficiency. The plan addresses the specific requirements of social media platforms, where recognising named entities plays a crucial role in understanding and analysing user-generated content

Flooding, a frequent natural disaster in Indonesia, is caused by several factors such as high-intensity rainfall, climate change, inadequate drainage and urban infrastructure challenges, impacting communities, infrastructure and economic activities. The lack of accurate and centralized data hinders government efforts to identify affected areas and respond effectively. Named Entity Recognition (NER), a machine learning-based information extraction tool, offers the potential for geocoding flood-related data from social media, such as Twitter. The purpose of this research is to develop a Named Entity Recognition (NER)-based model to extract location information from Twitter and visualize flood impacts through geocoding. The method used is a combination of Qualitative Analysis with Machine Learning and Geospatial Analysis to assess flooding impacts using Twitter data. Initially, a qualitative analysis of tweets extracts flood-related keywords to identify patterns. Then, Named Entity Recognition (NER) identifies locations, which are converted into geographic coordinates through geocoding for map visualization. The results show that location extraction from flood-related tweets using the Named Entity Recognition (NER) model and geocoding produces very useful and accurate data. About 50% of the flood-related tweets included location tokens, which shows the importance of geographic information in understanding the impact of disasters. The location extraction process using the NER model proved to be effective, although there were some discrepancies between the extracted location tokens and the actual geographic data, especially at the more detailed location level. However, the evaluation results show that 99.5% of the extracted locations correspond to valid locations, especially in the Indonesian region. This shows that the use of the NER model and geocoding is highly effective in analyzing flood impacts and provides significant benefits in disaster management and geospatial analysis based on social media data.

Named entity recognition (NER) is a sequential labelling task in categorizing textual nuggets into specific types. Named entity boundary detection can be recognized as a prominent research area under the NER domain which has been heavily adapted for information extraction, event extraction, information retrieval, sentiment analysis etc. Named entities (NE) can be identified as per flat NEs and nested NEs in nature and limited research attempts have been made for nested NE boundary detection. NER in low resource settings has been identified as a current trend. This research work has been scoped down to unveil the uniqueness in NE boundary detection based on Sinhala related contents which have been extracted from social media. The prime objective of this research attempt is to enhance the approach of named entity boundary detection. Considering the low resource settings, as the initial step, the linguistic patterns, complexity matrices and structures of the extracted social media statements have been analyzed further. A dedicated corpus of more than 100,000 tuples of Sinhala related social media content has been annotated by an expert panel. As per the scientific novelties, NE head word detection loss function, which was introduced in HelaNER 1.0, has been further improved and the NE boundary detection has been further enhanced through tuning up the stack pointer networks. Additionally, NE linking has been improved as a by-product of the previously mentioned enhancements. Various experimentations have been conducted, evaluated and the outcome has revealed that our enhancements have achieved the state-of-art performance over the existing baselines.

Named Entity Recognition (NER) is the fundamental task for Natural Language Processing (NLP) and the initial step in building a Knowledge Graph (KG). Recently, BERT (Bidirectional Encoder Representations from Transformers), which is a pre-training model, has achieved state-of-the-art (SOTA) results in various NLP tasks, including the NER. However, Chinese NER is still a more challenging task for BERT because there are no physical separations between Chinese words, and BERT can only obtain the representations of Chinese characters. Nevertheless, the Chinese NER cannot be well handled with character-level representations, because the meaning of a Chinese word is quite different from that of the characters, which make up the word. ERNIE (Enhanced Representation through kNowledge IntEgration), which is an improved pre-training model of BERT, is more suitable for Chinese NER because it is designed to learn language representations enhanced by the knowledge masking strategy. However, the potential of ERNIE has not been fully explored. ERNIE only utilizes the token-level features and ignores the sentence-level feature when performing the NER task. In this paper, we propose the ERNIE-Joint, which is a joint model based on ERNIE. The ERNIE-Joint can utilize both the sentence-level and token-level features by joint training the NER and text classification tasks. In order to use the raw NER datasets for joint training and avoid additional annotations, we perform the text classification task according to the number of entities in the sentences. The experiments are conducted on two datasets: MSRA-NER and Weibo. These datasets contain Chinese news data and Chinese social media data, respectively. The results demonstrate that the ERNIE-Joint not only outperforms BERT and ERNIE but also achieves the SOTA results on both datasets.

Software engineering social content, such as Q&A discussions on Stack Overflow, has become a wealth of information on software engineering. This textual content is centered around software-specific entities, and their usage patterns, issues-solutions, and alternatives. However, existing approaches to analyzing software engineering texts treat software-specific entities in the same way as other content, and thus cannot support the recent advance of entity-centric applications, such as direct answers and knowledge graph. The first step towards enabling these entity-centric applications for software engineering is to recognize and classify software-specific entities, which is referred to as Named Entity Recognition (NER) in the literature. Existing NER methods are designed for recognizing person, location and organization in formal and social texts, which are not applicable to NER in software engineering. Existing information extraction methods for software engineering are limited to API identification and linking of a particular programming language. In this paper, we formulate the research problem of NER in software engineering. We identify the challenges in designing a software-specific NER system and propose a machine learning based approach applied on software engineering social content. Our NER system, called S-NER, is general for software engineering in that it can recognize a broad category of software entities for a wide range of popular programming languages, platform, and library. We conduct systematic experiments to evaluate our machine learning based S-NER against a well-designed rule-based baseline system, and to study the effectiveness of widely-adopted NER techniques and features in the face of the unique characteristics of software engineering social content.

This study explores how audiences seek information from internet and social media platforms, and considers what factors affect social media use during a crisis. The paper is based on research conducted via a survey involving 162 active followers selected from the 875,200 followers of the Indonesia Train Company: PT Kereta Api Commuter Line official Twitter account (Info Commuter Line @CommuterLine). The study proposes the Simplified Social Mediated Crisis Communication Model (SSMCC) as a variation on the original Social-Mediated Crisis Communication (SMCC) Model by Jin & Liu (2010). This variation is based on the argument that during a crisis, audiences located nearby typically rely on social media (usually accessed via a mobile phone) rather than a traditional media outlet when seeking information. This study concludes that some of the themes related to the use of social media to search for information during a crisis, and word of mouth (WOM) communication, are present in the Social-Mediated Crisis Communication (SMCC) communication model. This study also discusses the differences between the original SMCC model and the Simplified Social-Mediated Crisis Communication model proposed by the researcher. There was no evidence of an inactive social media user’s influence on information retrieval during a crisis; in addition, there is no role of traditional media as a source of information retrieval during a crisis. This research contributes to developing scientific knowledge and practices in Indonesia.
 Keywords: crisis communication, social media, information search, simplified social mediated crisis communication model, social media followers