Stop Words Research Articles

Development of computational linguistic resources for automated detection of textual cyberbullying threats in Roman Urdu language

Automatic Cyberbullying detection has remained very challenging task since social media content and conversations are usually posted in unstructured free-text form leaving behind the language norms. The major concern and gap in formulating cyberbullying detection strategies is scarcity of available linguistic resources typically for newly evolved languages. Roman Urdu has recently emerged and hence is a resource poor language. Urdu has been widely known as the national language of Pakistan. However, because of socio-cultural and multilingual aspects, Roman Urdu is used widely on the Internet by Asians and more specifically Pakistanis. To fulfil the above stated gap, this research work presents guidelines for data annotation process and developed two linguistic resources: (i) Annotated corpus in Roman Urdu Language for cyberaggression and offensive language detection. The process of data annotation involved bilingual annotators instead of crowdsourcing. It has the benefit of correctly annotating instances that constitute clear cases of cyberbullying without compromising data quality. The developed corpus is highly balanced (with almost negligible skew) unlike most of the existing corpuses even in mature languages. (ii) Processing textual information for NLP tasks involves Stop-word elimination as a sub phase. Stop words carry least semantic information and increase feature space as compared to the other tokens and index terms in corpora. We have developed domain specific stop words for Roman Urdu Language considering all the lexical variants and typically in the context of aggression detection and collected data. The work has been carried out using python programming language and Pycharm IDE.

Cyberbullying Sentiment Analysis with Word2Vec and One-Against-All Support Vector Machine

Depression and social anxiety are the two main negative impacts of cyberbullying. Unfortunately, a survey conducted by UNICEF on 3rd September 2019 showed that 1 in 3 young people in 30 countries had been victims of cyberbullying. Sentiment analysis research will be conducted to detect a comment that contains cyberbullying. Dataset of cyberbullying is obtained from the Kaggle website, named, Toxic Comment Classification Challenge. The pre-processing process consists of 4 stages, namely comment generalization (convert text into lowercase and remove punctuation), tokenization, stop words removal, and lemmatization. Word Embedding will be used to conduct sentiment analysis by implementing Word2Vec. After that, One-Against-All (OAA) method with the Support Vector Machine (SVM) model will be used to make predictions in the form of multi labelling. The SVM model will go through a hyperparameter tuning process using Randomized Search CV. Then, evaluation will be carried out using Micro Averaged F1 Score to assess the prediction accuracy and Hamming Loss to assess the numbers of pairs of sample and label that are incorrectly classified. Implementation result of Word2Vec and OAA SVM model provide the best result for the data undergoing the process of pre-processing using comment generalization, tokenization, stop words removal, and lemmatization which is stored into 100 features in Word2Vec model. Micro Averaged F1 and Hamming Loss percentage that is produced by the tuned model is 83.40% and 15.13% respectively.
 
 Index Terms— Sentiment Analysis; Word Embedding; Word2Vec; One-Against-All; Support Vector Machine; Toxic Comment Classification Challenge; Multi Labelling

Domain-specific Stop Words in Malaysian Parliamentary Debates 1959 – 2018

Removal of stop words is essential in Natural Language Processing and text-related analysis. Existing works on Malay stop words are based on standard Malay and Quranic/Arabic translations into Malay. Thus, there is a lack of domain-specific stop word list, making it discordant for processing of Malay parliamentary discourse. In this paper, we propose a semantic approach towards identifying and removing Malay, conventional Malay spelling and English functional words in analysing a time-series corpus, namely the Malaysian Hansard Corpus (MHC), to extract a Malay specific-domain stop word list. The study utilised a combination of Z-method of most frequently occurring words, words that appear once, and the classic method. The dataset of the corpus evaluated comprised Parliament 1 (year 1959) to Parliament 13 (year 2018). The study then categorised the stop word list according to domain-specific related words. The resulting list comprised 587 stop words. New stop words that emerged from the MHC include parliamentary-related words like ‘ Berhormat’ (salutation to the members of the Parliament), ‘ Pertua’ (salutation to the Speaker of the House), ‘ ketawa’ (laugh) and ‘ tepuk’ (clap). Other than typical English stop words like ‘and’ and ‘the’, there are also words like ‘hon’ble’ (short for ‘Honourable’) and ‘honourable’. The list also includes stop words in conventional Malay spelling like ‘ untok ’ (for), ‘ lebeh ’ (more), and ‘ kapada ’ (to). The proposed set of stop words can be further utilised to assist natural language processing and text analysis.

Growth in eligibility criteria content and failure to accrue among National Cancer Institute (NCI)-affiliated clinical trials.

1515 Background: Cancer clinical trial accrual across diverse socioeconomic and demographic groups is a national priority, yet up to 20% of trials fail due to poor accrual. Eligibility criteria content may contribute to poor accrual, but effects are challenging to measure. We sought to evaluate growth of eligibility criteria within NCI-affiliated cancer trials and the impact on trial accrual over the past decade. Methods: We conducted a retrospective study with the Aggregate Analysis of ClinicalTrials.gov (AACT) (abstracted: 02/02/2021). We included NCI-affiliated, interventional Phase II or III trials that initiated between 01/01/2008 and 12/13/2018. We excluded active and recruiting trials that lacked accrual data on the Cancer Trials Support Unit website. Trials whose status was “Withdrawn”, “Terminated”, or “Suspended” due to low accrual, or had less than 50% target accrual after two years active were deemed accrual failures. Eligibility criteria were extracted from inclusion and exclusion criteria and complexity was estimated by the number of unique content words, calculated by removing duplicates and stop words from the word count. Association of unique word count with accrual failure was evaluated by univariable and multivariable logistic regressions, adjusting for other predictors of low accrual identified in earlier research. Results: Of 1197 trials included, 231 (19.3%) failed due to low accrual. Eligibility criteria increased in length from a median of 214 (IQR [23, 282]) unique content words in 2008 to 417 (IQR [289, 514]) in 2018. The rate of trial accrual failure increased with unique word count decile from 11.8% in the first decile (12 to 112 words) to 29.4% in the tenth decile (445 to 750 words) (P = 0.004). On multivariable analysis, unique word count remained independently associated with low accrual (OR: 1.07 per decile, 95%CI [1.01-1.13], P = 0.02), as did Phase III and metastatic disease settings (Table). Conclusions: Eligibility criteria content has increased dramatically in the last decade in NCI-affiliated trials. Increasing eligibility criteria content associates strongly with accrual failure, even after adjusting for multiple known predictors of accrual. These findings underscore the need for efforts to simplify eligibility criteria to improve trial accrual. Further investigation is ongoing to determine specific criteria qualities that portend accrual failure.[Table: see text]

Automatic Detection of Thyroid and Adrenal Incidentals Using Radiology Reports and Deep Learning

BackgroundComputed tomography (CT) is commonly performed when evaluating trauma patients with up to 55% showing incidental findings. Current workflows to identify and inform patients are time-consuming and prone to error. Our objective was to automatically identify thyroid and adrenal lesions in radiology reports using deep learning. Materials and methodsAll trauma patients who presented to an accredited Level 1 Trauma Center between January 2008 and January 2019 were included. Radiology reports of CT scans that included either a thyroid or adrenal gland were obtained. Preprocessing included word tokenization, removal of stop words, removal of punctuation, and replacement of misspellings. A word2vec model was trained using 1.4 million radiology reports. Both training and testing reports were selected at random, manually reviewed, and were considered the gold standard. True positive cases were defined as any lesions in the thyroid or adrenal gland, respectively. Training data was used to create models that would identify reports that contained either thyroid or adrenal lesions. Our primary outcomes were sensitivity and specificity of the models using predetermined thresholds on a separate testing dataset. ResultsA total of 51,771 reports were identified on 35,859 trauma patients. A total of 1,789 reports were annotated for training and 500 for testing. The thyroid model predictions resulted in a 90.0% sensitivity and 95.3% specificity. The adrenal model predictions resulted in a 92.3% sensitivity and a 91.1% specificity. A total of 240 reports were confirmed to have thyroid incidentals (mean age 69.1 yrs ± 18.9, 35% M) and 214 reports with adrenal incidentals (mean age 68.7 yrs ± 16.9, 50.5% M). ConclusionsBoth the thyroid and adrenal models have excellent performance with sensitivities and specificities in the 90s. Our deep learning model has the potential to reduce administrative costs and improve the process of informing patients.

Sentiment Analysis on Twitter Data by Using Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM)

Twitter sentiment analysis is an automated process of analyzing the text data which determining the opinion or feeling of public tweets from the various fields. For example, in marketing field, political field huge number of tweets is posting with hash tags every moment via internet from one user to another user. This sentiment analysis is a challenging task for the researchers mainly to correct interpretation of context in which certain tweet words are difficult to evaluate what truly is negative and positive statement from the huge corpus of tweet data. This problem violates the integrity of the system and the user reliability can be significantly reduced. In this paper, we identify the each tweet word and we are assigning a meaning into it. The feature work is combined with tweet words, word2vec, stop words and integrated into the deep learning techniques of Convolution neural network model and Long short Term Memory, these algorithms can identify the pattern of stop word counts with its own strategy. Those two models are well trained and applied for IMDB dataset which contains 50,000 movie reviews. With huge amount of twitter data is processed for predicting the sentimental tweets for classification. With the proposed methodology, the samples are experimentally collected from the real-time environment can be discriminated well and the efficacy of the system is improved. The result of Deep Learning algorithms aims to rate the review tweets and also able to identify movie review with testing accuracy as 87.74% and 88.02%.

Snippets of Folk Legends

A topic modelling tool was adapted to requirements for a collection of Swedish folk legends. To offer an overview of a list of folk legend texts, which had been automatically extracted by the topic modelling tool, snippet text versions of the folk legends were displayed. The snippets were constructed from the full-text versions of the legends using the sentences most relevant to the topics extracted by the topic modelling algorithm. In addition, collection-adapted data was constructed for performing a pre-processing of the folk legend texts, before they were submitted to the topic modelling algorithm. This data consisted of a collection-adapted stop word list and word lists for improving the quality of clusters of semantically similar words.

Optimization Assisted Convolutional Neural Network for Sentiment Analysis with Weighted Holoentropy-based Features

Analyzing and gathering the people’s reactions on product trading, public services, etc. are crucial. Sentiment analysis (also termed as opinion mining) is a usual dialogue preparing act that plans on discovering the sentiments after opinions in texts on changing subjects. This research work adopts a novel sentiment analysis approach that comprises six phases like (i) Pre-processing, (ii) Keyword extraction and its sentiment categorization, (iii) Semantic word extraction, (iv) Semantic similarity checking, (v) Feature extraction, and (vi) Classification. Accordingly, the Mongodb documented tweets initially underwent pre-processing with stop word removal, stemming, and blank space removal. Regarding the extracted keywords, the existing semantic words are derived after categorizing the sentiment of keywords. Additionally, the semantic similarity score is evaluated along with their keywords. The subsequent step is feature extraction, where the Holoentropy features such as cross Holoentropy and joint Holoentropy are formulated. Along with this, the extraction of weighted holoentropy features is the major work, where weight is multiplied with the holoentropy features. Moreover, in order to enhance the performance of classification results, the constant term utilized in evaluating the weight function is optimized. For this optimal tuning, a new, improved algorithm termed as Self Adaptive Moth Flame Optimization (SA-MFO) is introduced, which is the adaptive version of MFO algorithm. For classification, this paper aims to use the Deep Convolutional Neural network (DCNN), where the batch size is fine-tuned using the same SA-MFO algorithm. Finally, the performance of the proposed work is compared over other conventional models with respect to different performance measures.

An Analysis of the Safety of Medication Ordering Using Typo Correction within an Academic Medical System.

Spelling during medication ordering is prone to error, which can contribute to frustration, confusion, and, ultimately, errors. Typo correction can be utilized in an effort to mitigate the effects of misspellings by providing results even when no exact matches can be found. Although, typo correction can be beneficial in some scenarios, safety concerns have been raised when utilizing the functionality for medication ordering. Our primary objective was to analyze the effects of typo correction technology on medication errors within an academic medical system after implementation of the technology. Our secondary objective was to identify and provide additional recommendations to further improve the safety of the functionality. We analyzed 8 months of post-implementation data obtained from staff-reported medication errors and search query information obtained from the electronic health record. The reports were analyzed by two pharmacists in two phases: retrospective identification of errors occurring as a result of typo correction and prospective identification of potential errors with continued use of the functionality. In retrospective review of 2,603 reported medication-related errors, 26 were identified as potentially involving typo correction as a contributing factor. Six of these orders invoked typo correction, but none of the errors could be attributed to typo correction. In prospective review, a list of 40 error-prone words and terms were identified to be added as stop words and 407 medication synonyms were identified for removal from their associated medication records. Our results indicate, when properly implemented, typo correction does not cause additional medication errors. However, there may be benefit in implementing further precautions for preventing future errors.

Columnist Identification with Supervised Machine Learning using Punctuation and Stop Word Frequencies

Bu çalışmada köşe yazısı uzunluğundaki yazılarda noktalama ve etkisiz kelime kullanım sıklığı gibi basit özniteliklerin yazar tanımada yeterli olduğu ortaya konmuştur. Cumhuriyet gazetesi yazarlarından sıkça köşe yazan 6 adedi seçilerek her birinin çalışmanın başladığı tarihten geriye doğru son 120 köşe yazıları alınmış, her bir yazı için bir takım etkisiz kelime ve noktalama işaretlerinin kullanım sıklıklarına dayanan dokuz adet öznitelik elde edilmiştir. Sekiz gözetimli yapay öğrenme algoritması eğitildikten sonra yazının yazarını tanıma başarısı önişlemsiz ve önişlemden geçirilmiş veri kümelerinde ayrı ayrı ölçülmüş, asgari %82 ve azami %92 olmak üzere yüksek isabetli sonuçlar elde edilmiştir. Ölçeklemenin ve temel bileşen analizinin (PCA) başarıyı anlamlı miktarda değiştirmediği, ancak ölçekleme ve boyut azaltma yöntemi olarak doğrusal ayırtaç çözümlemenin (LDA) birlikte kullanılmasının en yakın komşu (kNN) ve Gaussian Naive Bayes (GNB) algoritmalarının yöntemlerin başarılarında yüksek anlamlı (p<0.001), destek vektör makineleri (SVM) algoritmasının başarısında ise anlamlı (p<0.05) bir fark yarattığı görülmüştür. Ayrıca karar ağacı temelli rasgele orman algoritmasında (RF) öznitelik önem analizi yapılarak cümle başına ortalama kelime sayısının ve virgül kullanma sıklığının en ayırıcı öznitelikler olduğu tespit edilmiştir.

Language dialect based speech emotion recognition through deep learning techniques

The primordial way of communication is through vocal signals, which pave the way for support between individuals in a social structure. Computer applications provide a way to create Automatic Speech Recognition (ASR) with a combination of Speech Emotion Recognition (SER) to detect and identify emotions in the speech signals. The semantic relatedness of words with abstract concepts proves to be complicated than concrete ideas. An ensemble of different clustering techniques is utilized to automatically segregate sense distinctions in the various dialects of sentences spoken to tackle this issue. The interpretation of word sense of a word may change with time and group of people. The proposed model maps characters to word sense with weights provided by Senticnet with trial-and-error methods and tuning. The proposed model utilizes stop words to distinguish word senses with 72.78% accuracy for regional dialects.

Aspect based sentiment analysis for demonetization tweets by optimized recurrent neural network using fire fly-oriented multi-verse optimizer

In this paper, it is proposed to understand the opinion of the public regarding the policy of demonetization that is implemented recently in India through Aspect-based Sentiment Analysis (ABSA) that predicts the sentiment of specific aspects present in the text. The major aim is to identify the relevant contexts for various aspects. Most of the conventional techniques have adopted attention mechanisms and deep learning concepts that decrease the prediction accuracy and generate huge noise. Another major disadvantage with the attention mechanisms is that the sentiment related to few context words alters with various aspects, and hence it cannot be concluded from itself alone. This paper adopts the optimized deep learning concept for performing the ABSA for demonetization tweets. The proposed model involves various phases such as pre-processing, aspect extraction, polarity feature extraction, and sentiment classification. Initially, the different demonetization tweets collected from the Kaggle dataset are taken. Pre-processing is done with the help of four phases like stop words removal, punctuation removal, lower case conversion, and stemming from minimizing the data to its reduced format. This pre-processed data is further performed with aspect extraction to extract the opinion words. These extracted aspect words are converted to the features with the help of polarity score computation and Word2vec. The weight of the polarity scores is optimized using hybridization of two meta-heuristic algorithms like FireFly Algorithm (FF), and Multi-Verse Optimization (MVO), and the new algorithm is termed as Fire Fly-oriented Multi-Verse Optimizer (FF-MVO). Further, combined features are subjected to a deep learning algorithm called Recurrent Neural Network (RNN). As a modification to the existing RNN, the hidden neurons are optimized by the hybrid FF-MVO, FF-MVO-RNN classifies the positive and negative sentiments. Finally, the comparative analysis of different machine learning algorithms proves the competent performance of the proposed model.

Building knowledge graphs of regulatory documentation based on semantic modeling and automatic term extraction

The paper proposes a new complex solution for automatic analysis and terms identification in regulatory and technical documentation (RTD). The task of terms identification in the documentation is one of the key issues in the digitalization dealing with the design and construction of buildings and structures. At the moment, the search and verification of RTD requirements is performed manually, which entails a significant number of errors. Automation of such tasks will significantly improve the quality of computer-aided design. The developed algorithm is based on such methods of natural language analysis as tokenization, search for lemmas and stems, analysis of stop words and word embeddings applied to tokens and phrases, part-of-speech tagging, syntactic annotation, etc. The experiments on the automatic extraction of terms from regulatory documents have shown great prospects of the proposed algorithm and its application for building knowledge graphs in the design domain. The recognition accuracy for 202 documents selected by experts was 79 % for the coincidence of names and 37 % for the coincidence of term identifiers. This is a comparable result with the known approaches to solving this problem. The results of the work can be used in computer-aided design systems based on Building information modeling (BIM) models, as well as to automate the examination of design documentation.

Code-mixed sentiment analysis of Indonesian language and Javanese language using Lexicon based approach

Nowadays mixing one language with another language either in spoken or written communication has become a common practice for bilingual speakers in daily conversation as well as in social media. Lexicon based approach is one of the approaches in extracting the sentiment analysis. This study is aimed to compare two lexicon models which are SentiNetWord and VADER in extracting the polarity of the code-mixed sentences in Indonesian language and Javanese language. 3,963 tweets were gathered from two accounts that provide code-mixed tweets. Pre-processing such as removing duplicates, translating to English, filter special characters, transform lower case and filter stop words were conducted on the tweets. Positive and negative word score from lexicon model was then calculated using simple mathematic formula in order to classify the polarity. By comparing with the manual labelling, the result showed that SentiNetWord perform better than VADER in negative sentiments. However, both of the lexicon model did not perform well in neutral and positive sentiments. On overall performance, VADER showed better performance than SentiNetWord. This study showed that the reason for the misclassified was that most of Indonesian language and Javanese language consist of words that were considered as positive in both Lexicon model.

Cross-domain sentiment analysis model on Indonesian YouTube comment

A cross-domain sentiment analysis (CDSA) study in the Indonesian language and tree-based ensemble machine learning is quite interesting. CDSA is useful to support the labeling process of cross-domain sentiment and reduce any dependence on the experts; however, the mechanism in the opinion unstructured by stop word, language expressions, and Indonesian slang words is unidentified yet. This study aimed to obtain the best model of CDSA for the opinion in Indonesia language that commonly is full of stop words and slang words in the Indonesian dialect. This study was purposely to observe the benefits of the stop words cleaning and slang words conversion in CDSA in the Indonesian language form. It was also to find out which machine learning method is suitable for this model. This study started by crawling five datasets of the comments on YouTube from 5 different domains. The dataset was copied into two groups: the dataset group without any process of stop word cleaning and slang word conversion and the dataset group to stop word cleaning and slang word conversion. CDSA model was built for each dataset group and then tested using two types of tree-based ensemble machine learning, i.e., Random Forest (RF) and Extra Tree (ET) classifier, and tested using three types of non-ensemble machine learning, including Naïve Bayes (NB), SVM, and Decision Tree (DT) as the comparison. Then, It can be suggested that the accuracy of CDSA in Indonesia Language increased if it still removed the stop words and converted the slang words. The best classifier model was built using tree-based ensemble machine learning, particularly ET, as in this study, the ET model could achieve the highest accuracy by 91.19%. This model is expected to be the CDSA technique alternative in the Indonesian language.

Research on the Experience of Users of Political Slogans in Ukraine

The study partly reveals “Zelenskyi’s phenomenon”, when a person without any political experience confidently won a victory over an experienced politician at the presidential and parliamentary elections. The paper considered neuropsychological understanding of a brand as a multi-modal image with emotional connection and as an artificial addiction. Specific features of the perception of political slogans were studied with EMOTIV Epoc+ 14-channel mobile neurointerface and EmotivPRO and EMOTIV Brain Activity Map software. The ranking of slogans in terms of the efficiency of perception of the individuals of 40-60 years old was carried out on the basis of EEG and the cognitive and emotional indexes: obtained stress, interaction, interest, excitement, concentration, relaxation. The study involved 30 men and 30 women who intended to vote in the presidential elections of 2019. It was established which slogans are the best, good, average, ambiguous, with little effect, ineffective, with a negative effect. It was determined that the most effective and at the same time efficient slogan that evokes emotions and really encourages to support is PRESIDENT IS PEOPLE’S SERVANT. The best slogan that appeals to support it is “We Are Ukraine”, “New Policy of Ukraine”, “Country of Strong People!” The basic cognitive and emotional indexes that would contribute to the creation of effective psychological impact on voters’ behavior are the presence in the slogan of the word “Ukraine”, the avoidance of the so-called “stop words” (for women it is “army” and everything related to violence and death, and for men it is everything related to the provision of material benefits), the use of religious sentimentality in women and gender differences in slogans targeting. The value of the studied phenomenon and the efficiency of slogans and other media products before launching them into mass advertising has been proved.

Sentiment analysis on newspaper article reviews: contribution towards improved rider optimization-based hybrid classifier

PurposeUp to date development in sentiment analysis has resulted in a symbolic growth in the volume of study, especially on more subjective text types, namely, product or movie reviews. The key difference between these texts with news articles is that their target is defined and unique across the text. Hence, the reviews on newspaper articles can deal with three subtasks: correctly spotting the target, splitting the good and bad content from the reviews on the concerned target and evaluating different opinions provided in a detailed manner. On defining these tasks, this paper aims to implement a new sentiment analysis model for article reviews from the newspaper.Design/methodology/approachHere, tweets from various newspaper articles are taken and the sentiment analysis process is done with pre-processing, semantic word extraction, feature extraction and classification. Initially, the pre-processing phase is performed, in which different steps such as stop word removal, stemming, blank space removal are carried out and it results in producing the keywords that speak about positive, negative or neutral. Further, semantic words (similar) are extracted from the available dictionary by matching the keywords. Next, the feature extraction is done for the extracted keywords and semantic words using holoentropy to attain information statistics, which results in the attainment of maximum related information. Here, two categories of holoentropy features are extracted: joint holoentropy and cross holoentropy. These extracted features of entire keywords are finally subjected to a hybrid classifier, which merges the beneficial concepts of neural network (NN), and deep belief network (DBN). For improving the performance of sentiment classification, modification is done by inducing the idea of a modified rider optimization algorithm (ROA), so-called new steering updated ROA (NSU-ROA) into NN and DBN for weight update. Hence, the average of both improved classifiers will provide the classified sentiment as positive, negative or neutral from the reviews of newspaper articles effectively.FindingsThree data sets were considered for experimentation. The results have shown that the developed NSU-ROA + DBN + NN attained high accuracy, which was 2.6% superior to particle swarm optimization, 3% superior to FireFly, 3.8% superior to grey wolf optimization, 5.5% superior to whale optimization algorithm and 3.2% superior to ROA-based DBN + NN from data set 1. The classification analysis has shown that the accuracy of the proposed NSU − DBN + NN was 3.4% enhanced than DBN + NN, 25% enhanced than DBN and 28.5% enhanced than NN and 32.3% enhanced than support vector machine from data set 2. Thus, the effective performance of the proposed NSU − ROA + DBN + NN on sentiment analysis of newspaper articles has been proved.Originality/valueThis paper adopts the latest optimization algorithm called the NSU-ROA to effectively recognize the sentiments of the newspapers with NN and DBN. This is the first work that uses NSU-ROA-based optimization for accurate identification of sentiments from newspaper articles.

AN EXPERIMENTAL ANALYSIS ON ECOMMERCE REVIEWS,WITH SENTIMENT CLASSIFICATION USING OPINION MINING ON WEB

Sentiment analysis is a big branch in the field of natural language processing. Sentiment analysis mainly text based analysis, but there are some challenges that make it difficult as compared to traditional text based analysis. This paper empathizes on the need of an attempt to improve research process and progress of sentiment analysis on the basis of investigation. Outcome of the analysis are summarized in this paper. This paper analyze the reviews of products manually by collecting data in the form of a excel file. Then it will produce and classify the reviews as positive or negative comments to get the best product. Now it’s more relevant to automate reviews data it is growing exponentially. This method works by web scrapping reviews from e-commerce website. Data cleaning is applied to remove the unwanted data known as stop words. The features are identified. The feature can be camera, battery life etc. Obtain frequency across all the products and for all the reviews per feature. The intended work is to extract the features from the reviews and detecting the polarity for each aspect, thus resulting in feature extraction matrix (FEM). FEM matrix has each row as an observation for a product and each of the columns represent the feature. List of Products based on highest value of FEM for searched features and product recommendations are generated based on the user searched feature.

Intelligent pig‐raising knowledge question‐answering system based on neural network schemes

AbstractThe most important parts of Taiwan's agriculture are animal husbandry and the pig industry, of which the output value reached NT$75.6 billion in 2017. Taiwan has a high technical level of pig raising. However, practical pig‐raising skills rely mainly on the inheritance of mentoring experience. The livestock and pig breeding industry in Taiwan has no relevant pig breeding knowledge management information system and no intelligent knowledge question‐answering system. Therefore, this study designs and implements an intelligent knowledge question‐and‐answer system for pig farming. To identify intelligent questions and answers for raising livestock pigs, this study addresses the following issues: (a) to determine the semantic meaning of a sentence, the system needs to accurately interpret the meaning of a question and to identify the expression of a knowledge entity. Therefore, this study applies the lattice long‐short‐term memory (LSTM) and structured perceptron methods to parse sentences accurately and correctly perform word segmentation. A set of stop words for pig raising in Taiwan is initially established to ensure accurate sentence parsing; (b) to understand the intent of each sentence, the bidirectional gated recurrent init (bi‐GRU) method is adopted to realize the knowledge extraction of the livestock in the question and complete the intent detection and slot filling. The bi‐GRU extracts the correct livestock knowledge and classifies it into suitable topics; (c) the wide range of knowledge sources in questions often leads to unrelated vocabulary, repeated words, and structural loss in potential answers. To establish an effective knowledge search graph, the method infers implicit knowledge from the existing knowledge and conducts related knowledge retrieval based on the inference results. The knowledge data model is defined in the open standard resource description framework Knowledge filtering and knowledge reasoning strategies are presented to produce candidate answers to the livestock problem; (d) to obtain the final answer, most related works search established knowledge graphs, often producing multiple ambiguous candidate answers. The Siamese neural network (SNN) is adopted to obtain accurate answers. An SNN compares candidate answers to a livestock problem as two input values, previously trained by the bidirectional LSTM neural network. The final answer is determined from the cosine similarity value, which represents the highest relevance to the question. Finally, this study implements the intelligent pig‐raising knowledge question‐answering system based on the proposed methodology. The evaluation results reveal that the proposed system is accurate and practicable.

Evaluation and Emotional Analysis of Mobile Phone Sales of JD E-commerce Platform Based on LDA Model

With the rapid development of the Internet economy, the online transaction volume of e-commerce platforms has soared, and the purchase experience shared by users has become particularly important. How to quickly and effectively extract the required information from a large number of user reviews plays an important role in the decision-making of both consumers and businesses. This article conducts sentiment analysis on JD business platform Huawei mobile phone user comment information. First, this paper use crawler methods to collect user evaluation text information, and perform data preprocessing such as deduplication and cleaning of the collected raw data; then perform word segmentation on the processed text content, and filter stop words and worthless words; use the method based on emotional dictionary matching to analyze the sentiment tendency of the text. Finally, using the LDA topic analysis model, LDA topic analysis is performed on the sentiment classification text, and the topic words are extracted to obtain valuable internal information, and reasonable marketing strategies are proposed for the business.