scholarly journals Automatic morphological analysis on the material of Russian social media texts

10.29007/dlff ◽  
2019 ◽  
Author(s):  
Alena Fenogenova ◽  
Viktor Kazorin ◽  
Ilia Karpov ◽  
Tatyana Krylova
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Language Processing ◽  
Morphological Analysis ◽  
State Of The Art ◽  
Test Set ◽  
The Social ◽  
Media Texts

Automatic morphological analysis is one of the fundamental and significant tasks of NLP (Natural Language Processing). Due to special features of Internet texts, as they can be both normative texts (news, fiction, nonfiction) and less formal texts (such as blogs and texts from social networks), the morphological tagging has become non-trivial and an actual task. In this paper we describe our experiments in tagging of Internet texts presenting our approach based on deep learning. The new social media test set was created, that allows to compare our system with state-of-the-art open source analyzers on the social media texts material.

scholarly journals Twitter Sentiment Analysis Model

2021 ◽  
Vol 9 (VII) ◽  
pp. 296-302
Author(s):  
Pushkar Dubey
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Media ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Learning Approach ◽  
Analysis Model ◽  
Market Place ◽  
The Social

Social networks are the main resources to gather information about people’s opinion towards different topics as they spend hours daily on social media and share their opinion. Twitter is one of the social media that is gaining popularity. Twitter offers organizations a fast and effective way to analyze customers’ perspectives toward the critical to success in the market place. Developing a program for sentiment analysis is an approach to be used to computationally measure customers’ perceptions. .We use natural language processing and machine learning concepts to create a model for analysis . In this paper we are discussing how we can create a model for analysis of twittes which is trained by various nlp , machine learning and Deep learning Approach.

Extracting Events from Social Media Using NLP

2017 ◽  
pp. 43-48
Author(s):  
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Natural Language Processing ◽  
Language Processing ◽  
Scattered Data ◽  
Huge Data ◽  
Time Period ◽  
Event Category ◽  
The Social ◽  
Extract Information

Now a day’s Social media is major channel of communication between individuals and organizations. Huge data is available over the social networks, so it is important and essential to analyze this data to extract information. The data on social media is very much scattered, to extract an information it needs to be organized. Natural Language Processing (NLP) techniques are used to analyze the scattered data to fetch information for targeted entities (Event, Category, Date, Place, and Time period). The extracted information it is listed on a database and can be used in several ways. In this paper, a model is proposed which categorize event by their types, Date Place and Time. The results show this model can categorize the 90% events.

scholarly journals Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts

2017 ◽  
Vol 24 (4) ◽  
pp. 813-821 ◽  
Author(s):  
Anne Cocos ◽  
Alexander G Fiks ◽  
Aaron J Masino
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Recurrent Neural Network ◽  
State Of The Art ◽  
Detection Performance ◽  
Word Embeddings

Abstract Objective Social media is an important pharmacovigilance data source for adverse drug reaction (ADR) identification. Human review of social media data is infeasible due to data quantity, thus natural language processing techniques are necessary. Social media includes informal vocabulary and irregular grammar, which challenge natural language processing methods. Our objective is to develop a scalable, deep-learning approach that exceeds state-of-the-art ADR detection performance in social media. Materials and Methods We developed a recurrent neural network (RNN) model that labels words in an input sequence with ADR membership tags. The only input features are word-embedding vectors, which can be formed through task-independent pretraining or during ADR detection training. Results Our best-performing RNN model used pretrained word embeddings created from a large, non–domain-specific Twitter dataset. It achieved an approximate match F-measure of 0.755 for ADR identification on the dataset, compared to 0.631 for a baseline lexicon system and 0.65 for the state-of-the-art conditional random field model. Feature analysis indicated that semantic information in pretrained word embeddings boosted sensitivity and, combined with contextual awareness captured in the RNN, precision. Discussion Our model required no task-specific feature engineering, suggesting generalizability to additional sequence-labeling tasks. Learning curve analysis showed that our model reached optimal performance with fewer training examples than the other models. Conclusions ADR detection performance in social media is significantly improved by using a contextually aware model and word embeddings formed from large, unlabeled datasets. The approach reduces manual data-labeling requirements and is scalable to large social media datasets.

scholarly journals Intelligent Estimation of Social Media Sentimental Features using Deep Learning with Natural Language Processing Strategies

2021 ◽  
Vol 10 (6) ◽  
pp. 74-79
Author(s):  
Sarojini Yarramsetti ◽  
Anvar Shathik J ◽  
Renisha. P.S.
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Social Network ◽  
Natural Language ◽  
Language Processing ◽  
Digital World ◽  
The Social ◽  
Learning Principles ◽  
The Voice

In this digital world, experience sharing, knowledge exploration, taught posting and other related social exploitations are common to every individual as well as social media/network such as FaceBook, Twitter, etc plays a vital role in such kinds of activities. In general, many social network based sentimental feature extraction details and logics are available as well as many researchers work on that domain for last few years. But all those research specification are narrowed in the sense of building a way for estimating the opinions and sentiments with respect to the tweets and posts the user raised on the social network or any other related web interfacing medium. Many social network schemes provides an ability to the users to push the voice tweets and voice messages, so that the voice messages may contain some harmful as well as normal and important contents. In this paper, a new methodology is designed called Intensive Deep Learning based Voice Estimation Principle (IDLVEP), in which it is used to identify the voice message content and extract the features based on the Natural Language Processing (NLP) logic. The association of such Deep Learning and Natural Language Processing provides an efficient approach to build the powerful data processing model to identify the sentimental features from the social networking medium. This hybrid logic provides support for both text based and voice based tweet sentimental feature estimations. The Natural Language Processing principles assists the proposed approach of IDLVEP to extracts the voice content from the input message and provides a raw text content, based on that the deep learning principles classify the messages with respect to the estimation of harmful or normal tweets. The tweets raised by the user are initially sub-divided into two categories such as voice tweets and text tweets. The voice tweets will be taken care by the NLP principles and the text enabled tweets will be handled by means of deep learning principles, in which the voice tweets are also extracted and taken care by the deep learning principle only. The social network has two different faces such as provides support to developments as well as the same it provides a way to access that for harmful things. So, that this approach of IDLVEP identifies the harmful contents from the user tweets and remove that in an intelligent manner by using the proposed approach classification strategies. This paper concentrates on identifying the sentimental features from the user tweets and provides the harm free social network environment to the society.

Detecting Fake News Using Deep Learning and NLP

2021 ◽  
pp. 117-133
Author(s):  
Uma Maheswari Sadasivam ◽  
Nitin Ganesan
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Reliable Information ◽  
Citizen Journalism ◽  
Fake News ◽  
Social Unrest ◽  
Safe Place ◽  
The Social

Fake news is the word making more talk these days be it election, COVID 19 pandemic, or any social unrest. Many social websites have started to fact check the news or articles posted on their websites. The reason being these fake news creates confusion, chaos, misleading the community and society. In this cyber era, citizen journalism is happening more where citizens do the collection, reporting, dissemination, and analyse news or information. This means anyone can publish news on the social websites and lead to unreliable information from the readers' points of view as well. In order to make every nation or country safe place to live by holding a fair and square election, to stop spreading hatred on race, religion, caste, creed, also to have reliable information about COVID 19, and finally from any social unrest, we need to keep a tab on fake news. This chapter presents a way to detect fake news using deep learning technique and natural language processing.

On the Privacy and Utility of Anonymized Social Networks

2013 ◽  
Vol 4 (2) ◽  
pp. 1-34 ◽  
Author(s):  
Yi Song ◽  
Xuesong Lu ◽  
Sadegh Nobari ◽  
Stéphane Bressan ◽  
Panagiotis Karras
Keyword(s):  
Social Networks ◽  
Social Media ◽  
State Of The Art ◽  
Social Groups ◽  
Trade Off ◽  
Private Lives ◽  
The Social ◽  
Before And After ◽  
Do So

One is either on Facebook or not. Of course, this assessment is controversial and its rationale arguable. It is nevertheless not far, for many, from the reason behind joining social media and publishing and sharing details of their professional and private lives. Not only the personal details that may be revealed, but also the structure of the networks are sources of invaluable information for any organization wanting to understand and learn about social groups, their dynamics and members. These organizations may or may not be benevolent. It is important to devise, design and evaluate solutions that guarantee some privacy. One approach that reconciles the different stakeholders’ requirement is the publication of a modified graph. The perturbation is hoped to be sufficient to protect members’ privacy while it maintains sufficient utility for analysts wanting to study the social media as a whole. In this paper, the authors try to empirically quantify the inevitable trade-off between utility and privacy. They do so for two state-of-the-art graph anonymization algorithms that protect against most structural attacks, the k-automorphism algorithm and the k-degree anonymity algorithm. The authors measure several metrics for a series of real graphs from various social media before and after their anonymization under various settings.

scholarly journals Biomedical Concept Recognition Using Deep Neural Sequence Models

2019 ◽  
Author(s):  
Negacy D. Hailu ◽  
Michael Bada ◽  
Asmelash Teka Hadgu ◽  
Lawrence E. Hunter
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
State Of The Art ◽  
Conditional Random Field ◽  
Concept Recognition ◽  
Performance Improvements ◽  
Art Performance

AbstractBackgroundthe automated identification of mentions of ontological concepts in natural language texts is a central task in biomedical information extraction. Despite more than a decade of effort, performance in this task remains below the level necessary for many applications.Resultsrecently, applications of deep learning in natural language processing have demonstrated striking improvements over previously state-of-the-art performance in many related natural language processing tasks. Here we demonstrate similarly striking performance improvements in recognizing biomedical ontology concepts in full text journal articles using deep learning techniques originally developed for machine translation. For example, our best performing system improves the performance of the previous state-of-the-art in recognizing terms in the Gene Ontology Biological Process hierarchy, from a previous best F1 score of 0.40 to an F1 of 0.70, nearly halving the error rate. Nearly all other ontologies show similar performance improvements.ConclusionsA two-stage concept recognition system, which is a conditional random field model for span detection followed by a deep neural sequence model for normalization, improves the state-of-the-art performance for biomedical concept recognition. Treating the biomedical concept normalization task as a sequence-to-sequence mapping task similar to neural machine translation improves performance.

scholarly journals Text: An R-package for Analyzing and Visualizing Human Language Using Natural Language Processing and Deep Learning

2021 ◽  
Author(s):  
Oscar Nils Erik Kjell ◽  
H. Andrew Schwartz ◽  
Salvatore Giorgi
Keyword(s):  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Rating Scale ◽  
State Of The Art ◽  
R Package ◽  
Language Models ◽  
Categorical Variables ◽  
Human Language

The language that individuals use for expressing themselves contains rich psychological information. Recent significant advances in Natural Language Processing (NLP) and Deep Learning (DL), namely transformers, have resulted in large performance gains in tasks related to understanding natural language such as machine translation. However, these state-of-the-art methods have not yet been made easily accessible for psychology researchers, nor designed to be optimal for human-level analyses. This tutorial introduces text (www.r-text.org), a new R-package for analyzing and visualizing human language using transformers, the latest techniques from NLP and DL. Text is both a modular solution for accessing state-of-the-art language models and an end-to-end solution catered for human-level analyses. Hence, text provides user-friendly functions tailored to test hypotheses in social sciences for both relatively small and large datasets. This tutorial describes useful methods for analyzing text, providing functions with reliable defaults that can be used off-the-shelf as well as providing a framework for the advanced users to build on for novel techniques and analysis pipelines. The reader learns about six methods: 1) textEmbed: to transform text to traditional or modern transformer-based word embeddings (i.e., numeric representations of words); 2) textTrain: to examine the relationships between text and numeric/categorical variables; 3) textSimilarity and 4) textSimilarityTest: to computing semantic similarity scores between texts and significance test the difference in meaning between two sets of texts; and 5) textProjection and 6) textProjectionPlot: to examine and visualize text within the embedding space according to latent or specified construct dimensions (e.g., low to high rating scale scores).

scholarly journals Transformer-Based Decoder Designs for Semantic Segmentation on Remotely Sensed Images

2021 ◽  
Vol 13 (24) ◽  
pp. 5100
Author(s):  
Teerapong Panboonyuen ◽  
Kulsawasd Jitkajornwanich ◽  
Siam Lawawirojwong ◽  
Panu Srestasathiern ◽  
Peerapon Vateekul
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Language Processing ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Landsat 8 ◽  
Convolutional Network ◽  
Image Labeling ◽  
Feature Pyramid

Transformers have demonstrated remarkable accomplishments in several natural language processing (NLP) tasks as well as image processing tasks. Herein, we present a deep-learning (DL) model that is capable of improving the semantic segmentation network in two ways. First, utilizing the pre-training Swin Transformer (SwinTF) under Vision Transformer (ViT) as a backbone, the model weights downstream tasks by joining task layers upon the pretrained encoder. Secondly, decoder designs are applied to our DL network with three decoder designs, U-Net, pyramid scene parsing (PSP) network, and feature pyramid network (FPN), to perform pixel-level segmentation. The results are compared with other image labeling state of the art (SOTA) methods, such as global convolutional network (GCN) and ViT. Extensive experiments show that our Swin Transformer (SwinTF) with decoder designs reached a new state of the art on the Thailand Isan Landsat-8 corpus (89.8% F1 score), Thailand North Landsat-8 corpus (63.12% F1 score), and competitive results on ISPRS Vaihingen. Moreover, both our best-proposed methods (SwinTF-PSP and SwinTF-FPN) even outperformed SwinTF with supervised pre-training ViT on the ImageNet-1K in the Thailand, Landsat-8, and ISPRS Vaihingen corpora.

Sign in / Sign up

Export Citation Format

Share Document