NLWSNet: a weakly supervised network for visual sentiment analysis in mislabeled web images

2020 ◽  
Vol 21 (9) ◽  
pp. 1321-1333
Author(s):  
Luo-yang Xue ◽  
Qi-rong Mao ◽  
Xiao-hua Huang ◽  
Jie Chen
Keyword(s):  
Sentiment Analysis ◽  
Web Images ◽  
Weakly Supervised

scholarly journals CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

2018 ◽  
pp. 139-154 ◽  
Author(s):  
Sheng Guo ◽  
Weilin Huang ◽  
Haozhi Zhang ◽  
Chenfan Zhuang ◽  
Dengke Dong ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Large Scale ◽  
Weakly Supervised Learning ◽  
Web Images ◽  
Weakly Supervised

Weakly Supervised Sentiment-Specific Region Discovery for VSA

2020 ◽  
Author(s):  
Luoyang Xue ◽  
Ang Xu ◽  
Qirong Mao ◽  
Lijian Gao ◽  
Jie Chen
Keyword(s):  
Sentiment Analysis ◽  
State Of The Art ◽  
Multiple Instance Learning ◽  
Local Information ◽  
Specific Region ◽  
Convolution Kernels ◽  
Weakly Supervised ◽  
Candidate Regions ◽  
Region Discovery ◽  
Object Level

Abstract Local information has significant contributions to visual sentiment analysis (VSA). Recent studies about local region discovery need manually annotate region location. Affective local information learning and automatic discovery of sentiment-specific region are still the challenges in VSA. In this paper, we propose an end-to-end VSA method for weakly supervised sentiment-specific region discovery. Our method contains two branches: an automatic sentiment-specific region discovery branch and a sentiment analysis branch. In the sentiment-specific region discovery branch, a region proposal network with multiple convolution kernels is proposed to generate candidate affective regions. Then, we design the multiple instance learning (MIL) loss to remove redundant and noisy candidate regions. Finally, the sentiment analysis branch integrates both holistic and localized information obtained in the first branch by feature map coupling for final sentiment classification. Our method automatically discovers sentiment-specific regions by the constraint of MIL loss function without object-level labels. Quantitative and qualitative evaluations on four benchmark affective datasets demonstrate that our proposed method outperforms the state-of-the-art methods.

scholarly journals Aspect-Based Sentiment Analysis Using Aspect Map

2019 ◽  
Vol 9 (16) ◽  
pp. 3239
Author(s):  
Yunseok Noh ◽  
Seyoung Park ◽  
Seong-Bae Park
Keyword(s):  
Sentiment Analysis ◽  
Opinion Mining ◽  
State Of The Art ◽  
Positional Information ◽  
Specific Aspect ◽  
Classification Model ◽  
Neural Models ◽  
Single Text ◽  
Proposed Model ◽  
Weakly Supervised

Aspect-based sentiment analysis (ABSA) is the task of classifying the sentiment of a specific aspect in a text. Because a single text usually has multiple aspects which are expressed independently, ABSA is a crucial task for in-depth opinion mining. A key point of solving ABSA is to align sentiment expressions with their proper target aspect in a text. Thus, many recent neural models have applied attention mechanisms to learning the alignment. However, it is problematic to depend solely on attention mechanisms to achieve this, because most sentiment expressions such as “nice” and “bad” are too general to be aligned with a proper aspect even through an attention mechanism. To solve this problem, this paper proposes a novel convolutional neural network (CNN)-based aspect-level sentiment classification model, which consists of two CNNs. Because sentiment expressions relevant to an aspect usually appear near the aspect expressions of the aspect, the proposed model first finds the aspect expressions for a given aspect and then focuses on the sentiment expressions around the aspect expressions to determine the final sentiment of an aspect. Thus, the first CNN extracts the positional information of aspect expressions for a target aspect and expresses the information as an aspect map. Even if there exist no data with annotations on direct relation between aspects and their expressions, the aspect map can be obtained effectively by learning it in a weakly supervised manner. Then, the second CNN classifies the sentiment of the target aspect in a text using the aspect map. The proposed model is evaluated on SemEval 2016 Task 5 dataset and is compared with several baseline models. According to the experimental results, the proposed model does not only outperform the baseline models but also shows state-of-the-art performance for the dataset.

scholarly journals Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding

2020 ◽  
Author(s):  
Jiaxin Huang ◽  
Yu Meng ◽  
Fang Guo ◽  
Heng Ji ◽  
Jiawei Han
Keyword(s):  
Sentiment Analysis ◽  
Weakly Supervised

Sentiment Analysis for Product Reviews Based on Weakly-Supervised Deep Embedding

2021 ◽  
Author(s):  
S Sindhura ◽  
S Phani Praveen ◽  
M.Aruna Safali ◽  
NidamanuruSrinivasa Rao
Keyword(s):  
Sentiment Analysis ◽  
Product Reviews ◽  
Deep Embedding ◽  
Weakly Supervised

scholarly journals Exploiting Web Images for Weakly Supervised Object Detection

2019 ◽  
Vol 21 (5) ◽  
pp. 1135-1146
Author(s):  
Qingyi Tao ◽  
Hao Yang ◽  
Jianfei Cai
Keyword(s):  
Object Detection ◽  
Web Images ◽  
Weakly Supervised
Sign in / Sign up

Export Citation Format

Share Document