Sentic LSTM: a Hybrid Network for Targeted Aspect-Based Sentiment Analysis

Ma, Yukun; Peng, Haiyun; Khan, Tahir Abbas; Wang, Zhaoxia; Hussain, Amir

doi:10.1007/s12559-018-9549-x

Cited by 269 publications

(108 citation statements)

References 35 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…A significant amount of research is still under way to infer human intention in simple human-robot interaction tasks with unsolved problems, never mind complex interaction tasks. The research community is still developing solutions for AI to be, interpretable [2][3][4], transparent and explainable [1] to allow humans to understand the intention of an AI and develop mutual predictability and shared understanding. It is tempting for some to claim that taking the human out AI guides, human performs: AI guiding a pilot to control the workload of air traffic controllers [41].…”

Section: Relationships Of Equals: Why Is Teaming Hard For Ai Agents?mentioning

confidence: 99%

Social Integration of Artificial Intelligence: Functions, Automation Allocation Logic and Human-Autonomy Trust

Abbass

2019

Cogn Comput

119

View full text Add to dashboard Cite

Artificial intelligence (AI) is finding more uses in the human society resulting in a need to scrutinise the relationship between humans and AI. Technology itself has advanced from the mere encoding of human knowledge into a machine to designing machines that "know how" to autonomously acquire the knowledge they need, learn from it and act independently in the environment. Fortunately, this need is not new; it has scientific grounds that could be traced back to the inception of computers. This paper uses a multidisciplinary lens to explore how the natural cognitive intelligence in a human could interface with the artificial cognitive intelligence of a machine. The scientific journey over the last 50 years will be examined to understand the Human-AI relationship, and to present the nature of, and the role of trust in, this relationship. Risks and opportunities sitting at the human-AI interface will be studied to reveal some of the fundamental technical challenges for a trustworthy human-AI relationship. The critical assessment of the literature leads to the conclusion that any social integration of AI into the human social system would necessitate a form of a relationship on one level or another in society, meaning that humans will "always" actively participate in certain decision-making loops-either in-the-loop or on-the-loop-that will influence the operations of AI, regardless of how sophisticated it is.

show abstract

Section: Relationships Of Equals: Why Is Teaming Hard For Ai Agents?mentioning

confidence: 99%

Social Integration of Artificial Intelligence: Functions, Automation Allocation Logic and Human-Autonomy Trust

Abbass

2019

Cogn Comput

119

View full text Add to dashboard Cite

show abstract

“…This could be done in two directions: (1) by modifying the parameters of the deep learning approaches; and, (2) by collecting and preparing more training data. Moreover, we envision the development of hybrid methods, such as advocated in [62], which combine neural networks with explicit knowledge.…”

Section: Discussionmentioning

confidence: 99%

Sentiment Analysis of Lithuanian Texts Using Traditional and Deep Learning Approaches

2019

View full text Add to dashboard Cite

We describe the sentiment analysis experiments that were performed on the Lithuanian Internet comment dataset using traditional machine learning (Naïve Bayes Multinomial—NBM and Support Vector Machine—SVM) and deep learning (Long Short-Term Memory—LSTM and Convolutional Neural Network—CNN) approaches. The traditional machine learning techniques were used with the features based on the lexical, morphological, and character information. The deep learning approaches were applied on the top of two types of word embeddings (Vord2Vec continuous bag-of-words with negative sampling and FastText). Both traditional and deep learning approaches had to solve the positive/negative/neutral sentiment classification task on the balanced and full dataset versions. The best deep learning results (reaching 0.706 of accuracy) were achieved on the full dataset with CNN applied on top of the FastText embeddings, replaced emoticons, and eliminated diacritics. The traditional machine learning approaches demonstrated the best performance (0.735 of accuracy) on the full dataset with the NBM method, replaced emoticons, restored diacritics, and lemma unigrams as features. Although traditional machine learning approaches were superior when compared to the deep learning methods; deep learning demonstrated good results when applied on the small datasets.

show abstract

“…Sentiment knowledge is exploited through pretraining the model with the sentiment labels of documents and freezing parameters of some layers. Ma et al [27] proposed a knowledge-rich solution to ABSA which respectively leveraged commonsense knowledge to model the aspect and its context by employing the LSTM. In order to explicitly integrate the explicit knowledge with implicit knowledge, they extended LSTM, termed Sentic LSTM.…”

Section: Related Workmentioning

confidence: 99%

Attention-based Sentiment Reasoner for aspect-based sentiment analysis

Liu

Shen

Zhang

et al. 2019

Hum. Cent. Comput. Inf. Sci.

View full text Add to dashboard Cite

Over the last decade, aspect-based sentiment analysis (ABSA) has been a rapidly growing field of natural language processing [1]. ABSA is a fine-grained sentiment analysis task which aims at detecting the polarity of an entity or an entity's attribute [2]. In ABSA, the aspect can be divided into two levels: aspect term (also called aspect target) and aspect category. An example sentence is provided in Fig. 1. For the sentence "Best Pastrami I ever had and great portion without being ridiculous, " the aspect terms are "Pastrami" and "portions, " respectively. Aspect categories are "FOOD#QUALITY" and "FOOD#STYLE_OPTIONS. " Obviously, a satisfactory method for an ABSA task should be applicable at both aspect levels. In the early days, traditional machine learning methods dominated as the method for an ABSA task, such as Support Vector Machine (SVM) [3]. However, these methods need feature engineering which is time consuming and laborious. Recently, deep learning methods have become increasingly popular for the sentiment analysis task, such as

show abstract

Sentic LSTM: a Hybrid Network for Targeted Aspect-Based Sentiment Analysis

Cited by 269 publications

References 35 publications

Social Integration of Artificial Intelligence: Functions, Automation Allocation Logic and Human-Autonomy Trust

Social Integration of Artificial Intelligence: Functions, Automation Allocation Logic and Human-Autonomy Trust

Sentiment Analysis of Lithuanian Texts Using Traditional and Deep Learning Approaches

Attention-based Sentiment Reasoner for aspect-based sentiment analysis

Contact Info

Product

Resources

About