Sentiment analysis through recurrent variants latterly on convolutional neural network of Twitter

Identification of influencers in complex networks by local information dimensionality

https://link.springer.com/content/pdf/10.1186/s43093-020-00021-0.pdf

Satisfaction and revisit intentions at fast food restaurants

Abstract This paper addresses the problem of Twitter sentiment analysis through a hybrid approach in which SentiWordNet (SWN)-based feature vector acts as input to the classification model Support Vector Machine. Our main focus is to handle lexical modifier negation during SWN score calculation for the improvement of classification performance. Thus, we present naive and novel shift approach in which negation acts as both sentiment-bearing word and modifier, and then we shift the score of words from SWN based on their contextual semantic, inferred from neighbouring words. Additionally, we augment negation accounting procedure with a few heuristics for handling the cases in which negation presence does not necessarily mean negation. Experimental results show that the contextual-based SWN feature vector obtained through shift polarity approach alone led to an improved Twitter sentiment analysis system that outperforms the traditional reverse polarity approach by 2–6%. We validate the effectiveness of our hybrid approach considering negation on benchmark Twitter corpus from SemEval-2013 Task 2 competition.

https://www.degruyter.com/document/doi/10.1515/jisys-2019-0106/pdf

Enhanced Twitter Sentiment Analysis Using Hybrid Approach and by Accounting Local Contextual Semantic

The important nodes identification has been an interesting problem in this issue. Several centrality methods have been proposed to solve this problem, but most previous methods have their own limitations. To address this problem more effectively, multi-local dimension (MLD) which is based on the fractal property is proposed to identify the vital spreaders in this paper. This proposed method considers the information contained in the box and q plays a weighting coefficient for this partition information. MLD would have different expressions with different values of q , and it would degenerate to local information dimension and variant of local dimension when q = 1 when q = 0 respectively, both of which have been effective identification methods for influential nodes. Thus, MLD would be a more general method which can degenerate to some existing centrality methods. In addition, different from classical methods, the node with low MLD would be more important in the network. Some real-world and theoretical complex networks and comparison methods are applied in this paper to show the effectiveness and reasonableness of this proposed method. The experiment results show the superiority of this proposed method.

Vital spreaders identification in complex networks with multi-local dimension

Analyzing massive user-generated microblogs is very crucial in many fields, attracting many researchers to study. However, it is very challenging to process such noisy and short microblogs. Most prior works only use texts to identify sentiment polarity and assume that microblogs are independent and identically distributed, which ignore microblogs are networked data. Therefore, their performance is not usually satisfactory. Inspired by two sociological theories (sentimental consistency and emotional contagion), in this paper, we propose a new method combining social context and topic context to analyze microblog sentiment. In particular, different from previous work using direct user relations, we introduce structure similarity context into social contexts and propose a method to measure structure similarity. In addition, we also introduce topic context to model the semantic relations between microblogs. Social context and topic context are combined by the Laplacian matrix of the graph built by these contexts and Laplacian regularization are added into the microblog sentiment analysis model. Experimental results on two real Twitter datasets demonstrate that our proposed model can outperform baseline methods consistently and significantly.

/pdf/microblog-sentiment-analysis-using-social-and-topic-context-5mvy9lnh6g.pdf

Microblog sentiment analysis using social and topic context.

Sentiment analysis is widely studied to extract opinions from user generated content (UGC), and various methods have been proposed in recent literature. However, these methods are likely to introduce sentiment bias, and the classification results tend to be positive or negative, especially for the lexicon-based sentiment classification methods. The existence of sentiment bias leads to poor performance of sentiment analysis. To deal with this problem, we propose a novel sentiment bias processing strategy which can be applied to the lexicon-based sentiment analysis method. Weight and threshold parameters learned from a small training set are introduced into the lexicon-based sentiment scoring formula, and then the formula is used to classify the reviews. In this paper, a completed sentiment classification framework is proposed. SentiWordNet (SWN) is used as the experimental sentiment lexicon, and review data of four products collected from Amazon are used as the experimental datasets. Experimental results show that the bias processing strategy reduces polarity bias rate (PBR) and improves performance of the lexicon-based sentiment analysis method.

/pdf/improving-the-performance-of-lexicon-based-review-sentiment-4i1ulfnz87.pdf

Improving the performance of lexicon-based review sentiment analysis method by reducing additional introduced sentiment bias.

Identifying a group of influential nodes in social networks help us understand the hierarchical structure of the network and make a better control the spread of information. Moreover, it can offer guidance in avoiding the breakdown of the power system and the Internet, identifying drug targets and essential proteins. Undoubtedly, most of the influence measures suffer the low resolution. The same score corresponds to multiple nodes. What’s worse is that the effect of overlapping between nodes is not fully considered. It causes resource waste in node selection. The purpose of this paper is to identify a set of distributed nodes with the strong propagation ability. Inspired by the interplay between the individuals and groups from sociological and complex networks, we propose a node ranking method based on the social conformity theory and community feature based on VoteRank. This proposed method calculates the node influence capability from two points of view, one is the individual, the other is the group. From the point of the individual, it quantifies the attractive power of the nodes with the feature of their neighbors based on the theory of conformity. It can distinguish the nodes with the same degree and similar structure. From the other point, it measures the initiating power with the scale of the community and the relative location of the node. Furthermore, a node selection strategy based on information coverage and community tightness is proposed to solve the problem of overlapping. Finally, node attractive power, initiating power and the node selection strategy are combined to improve VoteRank. The experimental results on real-world networks show the effectiveness of our methods. The results also explains that the enormous energy from the groups makes the node powerful.

Groups make nodes powerful: Identifying influential nodes in social networks based on social conformity theory and community features

Microblog sentiment analysis via embedding social contexts into an attentive LSTM

Microblog sentiment analysis has become a hot research area due to its wide applications. There are some methods utilizing social context, but they only built a global sentiment analysis model, failing to extract personalized expressions. Some personalized methods have been proposed to deal with this problem, but they suffer from data sparseness and inefficiency. Based on personalized sentiment analysis methods, we exploit social context information and capture users’ variable and distinctive expressions at a community level to handle these problems. In particular, we propose a collaborative microblog sentiment analysis approach. In our approach, two classifiers are constructed. One is the global microblog sentiment analysis model which can exploit the sentiment shared by all users. One is the community-specific microblog sentiment analysis model which can extract sentiment influenced by user personalities. In addition, we extract community similarity knowledge and employ it to improve the learning process of the community-specific sentiment model. Moreover, we incorporate social contexts into this model as regularization to encourage the sharing sentiment between connected microblogs. An accelerated algorithm is introduced to solve our model. Experiments on two real datasets show that our model can advance the performance of microblog sentiment classification effectively and outperform state-of-art methods significantly.

Xiaomei Zou

Papers

Microblog sentiment analysis using social and topic context.

Improving the performance of lexicon-based review sentiment analysis method by reducing additional introduced sentiment bias.

Groups make nodes powerful: Identifying influential nodes in social networks based on social conformity theory and community features

Microblog sentiment analysis via embedding social contexts into an attentive LSTM

Collaborative community-specific microblog sentiment analysis via multi-task learning