scholarly journals Deep semi-supervised learning with weight map for review helpfulness prediction

2021 ◽  
pp. 44-44
Author(s):  
Hua Yin ◽  
Zhensheng Hu ◽  
Yahui Peng ◽  
Zhijian Wang ◽  
Guanglong Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Mapping Method ◽  
Product Reviews ◽  
Purchasing Decisions ◽  
The Past ◽  
Review Helpfulness ◽  
Series Of Experiments ◽  
Novel Model ◽  
Weight Map

Helpful online product reviews, which includemassive information, have large impacts on customers? purchasing decisions. In most of e-commerce plat forms, the helpfulness of reviews are decided by the votes from other customers. Making full use of these reviews with votes has enormous commercial value, especially in product recommendation. It drives researchers to study the technologies about how to evaluate the review helpfulness automatically. Although Deep Neural Network(DNN), learning from the historical reviews and labels, computed by the votes, has demonstrated effective results, it still has suffered insufficient labeled reviews problem. When the helpfulness of a large number of reviews is unknown for lack of votes, or some useful latest reviews with less votes are submerged by the past reviews, the accuracy of current DNN model decreases quickly. Therefore, we propose an end-to-end deep semi-supervised learning model with weight map, which makes full use of the unlabeled reviews. The training process in this model is divided into three stages:obtaining base classifier by less labeled reviews, iteratively applying weight map strategy on large unlabeled reviews to obtain pseudo-labeled reviews, training on above combined reviews to obtain the re-training classifier. Based on this novel model, we develop an algorithm and conduct a series of experiments, on Amazon Review Dataset, from the aspects of the baseline neural network selection and the strategies comparisons, including two labeling and three weighting strategies. The experimental results demonstrate the effectiveness of our method on utilizing the unlabeled data. And our findings show that the model adopted batch labeling strategy and non-linear weight mapping method has achieved the best performance.

scholarly journals Snapshop-An Image Based Search Application

2021 ◽  
pp. 691-697
Author(s):  
Karan D. Argade ◽  
Dhanashree M. Gaware ◽  
Prajkta S. Umap ◽  
Savita P. Nalawade ◽  
Snehal Baravkar
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Pattern Matching ◽  
Image Recognition ◽  
Deep Neural Network ◽  
Fashion Industry ◽  
Purchasing Decisions ◽  
The Past ◽  
Product Features ◽  
Recognition Pattern

E-commerce has been growing rapidly over the past few years, Peoples uses them to buy and sell products. Since In these offline stores, they face many problems such as inability. For many online customers, image recognition of clothing and to identify the style, the color, and, in fact, it is a challenge to the sophistication of the fashion industry. In e-commerce, the online platform primarily offers text-based search capabilities. They can search many product searches, but they cannot manage searches based on product features, for example, colors or t-shirt patterns. Often, it is difficult for the user to make this determination features when searching for a product. Furthermore, an increasing number of consumers are depending on social media to make purchasing decisions. Consumers are trying to discover what is going on right now and are looking for the same things. This brings us to the need for a visual commerce platform, or a plan, which recommends products based on users, provided that the product images. The database uses a flexible neural network. You extract data using this deep neural network of image recognition, pattern matching and are very effective in testing fabric prediction.

scholarly journals A Hybrid CNN-Based Review Helpfulness Filtering Model for Improving E-Commerce Recommendation Service

2021 ◽  
Vol 11 (18) ◽  
pp. 8613
Author(s):  
Qinglong Li ◽  
Xinzhe Li ◽  
Byunghyun Lee ◽  
Jaekyeong Kim
Keyword(s):  
Neural Network ◽  
Recommender System ◽  
User Satisfaction ◽  
Short Term Memory ◽  
Positive Impact ◽  
Classification Model ◽  
Personalized Recommendation ◽  
Purchasing Decisions ◽  
Review Helpfulness ◽  
Information Exploration

As the e-commerce market grows worldwide, personalized recommendation services have become essential to users’ personalized items or services. They can decrease the cost of user information exploration and have a positive impact on corporate sales growth. Recently, many studies have been actively conducted using reviews written by users to address traditional recommender system research problems. However, reviews can include content that is not conducive to purchasing decisions, such as advertising, false reviews, or fake reviews. Using such reviews to provide recommendation services can lower the recommendation performance as well as a trust in the company. This study proposes a novel review of the helpfulness-based recommendation methodology (RHRM) framework to support users’ purchasing decisions in personalized recommendation services. The core of our framework is a review semantics extractor and a user/item recommendation generator. The review semantics extractor learns reviews representations in a convolutional neural network and bidirectional long short-term memory hybrid neural network for review helpfulness classification. The user/item recommendation generator models the user’s preference on items based on their past interactions. Here, past interactions indicate only records in which the user-written reviews of items are helpful. Since many reviews do not have helpfulness scores, we first propose a helpfulness classification model to reflect the review helpfulness that significantly impacts users’ purchasing decisions in personalized recommendation services. The helpfulness classification model is trained about limited reviews utilizing helpfulness scores. Several experiments with the Amazon dataset show that if review helpfulness information is used in the recommender system, performance such as the accuracy of personalized recommendation service can be further improved, thereby enhancing user satisfaction and further increasing trust in the company.

A Scientific Search for Altruism

2018 ◽  
Author(s):  
C. Daniel Batson
Keyword(s):  
Human Nature ◽  
Scientific Method ◽  
Laboratory Experiments ◽  
Fundamental Question ◽  
Empathic Concern ◽  
Altruistic Motivation ◽  
The Past ◽  
Past Half Century ◽  
Series Of Experiments ◽  
Past Half

This book provides an example of how the scientific method can be used to address a fundamental question about human nature. For centuries—indeed for millennia—the egoism–altruism debate has echoed through Western thought. Egoism says that the motivation for everything we do, including all of our seemingly selfless acts of care for others, is to gain one or another self-benefit. Altruism, while not denying the force of self-benefit, says that under certain circumstances we can care for others for their sakes, not our own. Over the past half-century, social psychologists have turned to laboratory experiments to provide a scientific resolution of this human nature debate. The experiments focused on the possibility that empathic concern—other-oriented emotion elicited by and congruent with the perceived welfare of someone in need—produces altruistic motivation to remove that need. With carefully constructed experimental designs, these psychologists have tested the nature of the motivation produced by empathic concern, determining whether it is egoistic or altruistic. This series of experiments has provided an answer to a fundamental question about what makes us tick. Framed as a detective story, the book traces this scientific search for altruism through the numerous twists and turns that led to the conclusion that empathy-induced altruism is indeed part of our nature. It then examines the implications of this conclusion—negative implications as well as positive—both for our understanding of who we are as humans and for how we might create a more humane society.

scholarly journals Multi-Scale Aggregation Graph Neural Networks Based on Feature Similarity for Semi-Supervised Learning

Entropy ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. 403
Author(s):  
Xun Zhang ◽  
Lanyan Yang ◽  
Bin Zhang ◽  
Ying Liu ◽  
Dong Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Structured Data ◽  
Similarity Matrix ◽  
Scale Feature ◽  
Multi Scale ◽  
Adjacent Node ◽  
Feature Similarity ◽  
The Mean ◽  
Graph Neural Networks

The problem of extracting meaningful data through graph analysis spans a range of different fields, such as social networks, knowledge graphs, citation networks, the World Wide Web, and so on. As increasingly structured data become available, the importance of being able to effectively mine and learn from such data continues to grow. In this paper, we propose the multi-scale aggregation graph neural network based on feature similarity (MAGN), a novel graph neural network defined in the vertex domain. Our model provides a simple and general semi-supervised learning method for graph-structured data, in which only a very small part of the data is labeled as the training set. We first construct a similarity matrix by calculating the similarity of original features between all adjacent node pairs, and then generate a set of feature extractors utilizing the similarity matrix to perform multi-scale feature propagation on graphs. The output of multi-scale feature propagation is finally aggregated by using the mean-pooling operation. Our method aims to improve the model representation ability via multi-scale neighborhood aggregation based on feature similarity. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our method compared to a variety of popular architectures.

scholarly journals Laplacian networks: bounding indicator function smoothness for neural networks robustness

2021 ◽  
Vol 10 ◽  
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Supervised Learning ◽  
Indicator Function ◽  
Training Data ◽  
Theoretical Justification ◽  
The Past ◽  
Noisy Examples

For the past few years, deep learning (DL) robustness (i.e. the ability to maintain the same decision when inputs are subject to perturbations) has become a question of paramount importance, in particular in settings where misclassification can have dramatic consequences. To address this question, authors have proposed different approaches, such as adding regularizers or training using noisy examples. In this paper we introduce a regularizer based on the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DL architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness on classical supervised learning vision datasets for various types of perturbations. We also show it can be combined with existing methods to increase overall robustness.

Assessing the Unacquainted: Inferred Reviewer Personality and Review Helpfulness

MIS Quarterly ◽  
2021 ◽  
Vol 45 (3) ◽  
pp. 1113-1148
Author(s):  
Angela Xia Liu ◽  
◽  
Yilin Li ◽  
Sean Xu ◽  
◽  
...  
Keyword(s):  
Personality Traits ◽  
Supervised Classification ◽  
Large Population ◽  
Superior Performance ◽  
Product Reviews ◽  
Review Helpfulness ◽  
Personality Theories ◽  
Deep Learning Model ◽  
Practical Implications

This work examines the question of who is more likely to provide future helpful reviews in the context of online product reviews by synergistically using personality theories and data analytics. It trains a deep learning model to infer a reviewer’s personality traits. This enables analyses to reveal the role of personality traits in review helpfulness among a large population of reviewers. We develop hypotheses on how personality traits are associated with review helpfulness, followed by hypotheses testing that confirms that higher review helpfulness is related to higher openness, conscientiousness, extraversion, and agreeableness and to lower emotional stability. These results suggest the appropriateness of using these five personality traits as inputs for developing a model for predicting future review helpfulness. Based on an ensemble model using supervised classification algorithms, we develop a predictive model and demonstrate its superior performance. Theoretical and practical implications are discussed.

IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK IN PREDICTING BIRTH RATE IN BATAM CITY USING BACKPROPAGATION METHOD

JURTEKSI ◽  
2021 ◽  
Vol 8 (1) ◽  
pp. 85-94
Author(s):  
Muhammad Jufri
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Family Planning ◽  
Population Growth ◽  
Birth Rate ◽  
The Past ◽  
Backpropagation Method ◽  
Artificial Neural ◽  
The Government ◽  
The City

Abstract: The population growth in Indonesia is increasing rapidly every year, so to help the government control the population growth through family planning programs, especially in the city of Batam. This study explains and describes one of the Artificial Terms Network methods, namely Backpropagation, where this method can predict what will happen in the future using data and information in the past. This study aims to predict the birth rate in the city of Batam to help the government with the family planning program. The data used is the annual data on the number of births in the city of Batam in 2016-2020 at The Civil Registry Office. To facilitate the analysis of research data, the data were tested using Matlab R2015b. In this study, the training process was carried out using 3 network architectures, namely 4-10-1, 5-18-1, and 4-43-1. Of these 3 architectures, the best is the 4-43-1 architecture with an accuracy rate of 91% and an MSE value of 0.0012205. The Backpropagation method can predict the amount of population growth in the city of Batam based on existing data in the past.           Keywords: artificial neural network; backpropagation; prediction   Abstrak: Pertumbuhan jumlah penduduk diindonesia yang setiap tahun meningkat dengan pesat, maka untuk membantu pemerintah mengendalikan jumlah pertumbuhan penduduk melalui program keluarga berencana khususnya dikota Batam. Penelitian ini  menjelaskan dan memaparkan tentang salah satu metode Jaringan Syarat Tiruan yaitu Backpropagation, dimana metode ini dapat memprediksi apa yang akan terjadi masa yang akan datang dengan menggunakan data dan informasi dimasa lalu. Penelitian ini bertujuan untuk memprediksi tingkat kelahiran di kota Batam sehingga membatu pemerintah untuk perencanaan keluarga berencana. Data yang digunakan yaitu data tahunan jumlah kelahiran di kota Batam pada tahun 2016-2020 pada Dinas Kependudukan dan Catatan Sipil. Untuk mempermudah analisis data penelitian maka, data diuji menggunakan Matlab R2015b. Pada penelitian ini dilakukan proses pelatihan menggunakan  3 arsitektur jaringan yaitu 4-10-1, 5-18-1, dan 4-43-1. Dari ke-3 arsitektur ini yang terbaik adalah arsitektur 4-43-1 dengan tingkat akurasi sebesar 91% dan nilai MSE 0,0012205. Metode backpropagation mampu memprediksi jumlah pertumbuhan penduduk di kota Batam berdasarkan data yang ada dimasa lalu. Kata kunci: backpropagation; jaringan syaraf tiruan; prediksi 

Sign in / Sign up

Export Citation Format

Share Document