Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"Sentiment Analysis": models, code, and papers

Learn from Structural Scope: Improving Aspect-Level Sentiment Analysis with Hybrid Graph Convolutional Networks

Apr 27, 2022
Lvxiaowei Xu, Xiaoxuan Pang, Jianwang Wu, Ming Cai, Jiawei Peng

Aspect-level sentiment analysis aims to determine the sentiment polarity towards a specific target in a sentence. The main challenge of this task is to effectively model the relation between targets and sentiments so as to filter out noisy opinion words from irrelevant targets. Most recent efforts capture relations through target-sentiment pairs or opinion spans from a word-level or phrase-level perspective. Based on the observation that targets and sentiments essentially establish relations following the grammatical hierarchy of phrase-clause-sentence structure, it is hopeful to exploit comprehensive syntactic information for better guiding the learning process. Therefore, we introduce the concept of Scope, which outlines a structural text region related to a specific target. To jointly learn structural Scope and predict the sentiment polarity, we propose a hybrid graph convolutional network (HGCN) to synthesize information from constituency tree and dependency tree, exploring the potential of linking two syntax parsing methods to enrich the representation. Experimental results on four public datasets illustrate that our HGCN model outperforms current state-of-the-art baselines.

* 9 pages, 5 figures, 4 tables 
Access Paper or Ask Questions

Exploiting BERT to improve aspect-based sentiment analysis performance on Persian language

Dec 02, 2020
H. Jafarian, A. H. Taghavi, A. Javaheri, R. Rawassizadeh

Aspect-based sentiment analysis (ABSA) is a more detailed task in sentiment analysis, by identifying opinion polarity toward a certain aspect in a text. This method is attracting more attention from the community, due to the fact that it provides more thorough and useful information. However, there are few language-specific researches on Persian language. The present research aims to improve the ABSA on the Persian Pars-ABSA dataset. This research shows the potential of using pre-trained BERT model and taking advantage of using sentence-pair input on an ABSA task. The results indicate that employing Pars-BERT pre-trained model along with natural language inference auxiliary sentence (NLI-M) could boost the ABSA task accuracy up to 91% which is 5.5% (absolute) higher than state-of-the-art studies on Pars-ABSA dataset.

Access Paper or Ask Questions

EmoWrite: A Sentiment Analysis-Based Thought to Text Conversion

Mar 03, 2021
A. Shahid, I. Raza, S. A. Hussain

Brain Computer Interface (BCI) helps in processing and extraction of useful information from the acquired brain signals having applications in diverse fields such as military, medicine, neuroscience, and rehabilitation. BCI has been used to support paralytic patients having speech impediments with severe disabilities. To help paralytic patients communicate with ease, BCI based systems convert silent speech (thoughts) to text. However, these systems have an inconvenient graphical user interface, high latency, limited typing speed, and low accuracy rate. Apart from these limitations, the existing systems do not incorporate the inevitable factor of a patient's emotional states and sentiment analysis. The proposed system EmoWrite implements a dynamic keyboard with contextualized appearance of characters reducing the traversal time and improving the utilization of the screen space. The proposed system has been evaluated and compared with the existing systems for accuracy, convenience, sentimental analysis, and typing speed. This system results in 6.58 Words Per Minute (WPM) and 31.92 Characters Per Minute (CPM) with an accuracy of 90.36 percent. EmoWrite also gives remarkable results when it comes to the integration of emotional states. Its Information Transfer Rate (ITR) is also high as compared to other systems i.e., 87.55 bits per min with commands and 72.52 bits per min for letters. Furthermore, it provides easy to use interface with a latency of 2.685 sec.

Access Paper or Ask Questions

MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis

May 08, 2020
Devamanyu Hazarika, Roger Zimmermann, Soujanya Poria

Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addressing this task, has been to develop sophisticated fusion techniques. However, the heterogeneous nature of the signals creates distributional modality gaps that pose significant challenges. In this paper, we aim to learn effective modality representations to aid the process of fusion. We propose a novel framework, MISA, which projects each modality to two distinct subspaces. The first subspace is modality invariant, where the representations across modalities learn their commonalities and reduce the modality gap. The second subspace is modality-specific, which is private to each modality and captures their characteristic features. These representations provide a holistic view of the multimodal data, which is used for fusion that leads to task predictions. Our experiments on popular sentiment analysis benchmarks, MOSI and MOSEI, demonstrate significant gains over state-of-the-art models. We also consider the task of Multimodal Humor Detection and experiment on the recently proposed UR_FUNNY dataset. Here too, our model fares better than strong baselines, establishing MISA as a useful multimodal framework.

Access Paper or Ask Questions

Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge

May 09, 2021
Yong Dai, Jian Liu, Jian Zhang, Hongguang Fu, Zenglin Xu

Sentiment analysis (SA) is an important research area in cognitive computation-thus in-depth studies of patterns of sentiment analysis are necessary. At present, rich resource data-based SA has been well developed, while the more challenging and practical multi-source unsupervised SA (i.e. a target domain SA by transferring from multiple source domains) is seldom studied. The challenges behind this problem mainly locate in the lack of supervision information, the semantic gaps among domains (i.e., domain shifts), and the loss of knowledge. However, existing methods either lack the distinguishable capacity of the semantic gaps among domains or lose private knowledge. To alleviate these problems, we propose a two-stage domain adaptation framework. In the first stage, a multi-task methodology-based shared-private architecture is employed to explicitly model the domain common features and the domain-specific features for the labeled source domains. In the second stage, two elaborate mechanisms are embedded in the shared private architecture to transfer knowledge from multiple source domains. The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain. And the second mechanism is a target-oriented ensemble (TOE) method, in which knowledge is transferred through a well-designed ensemble method. Extensive experiment evaluations verify that the performance of the proposed framework outperforms unsupervised state-of-the-art competitors. What can be concluded from the experiments is that transferring from very different distributed source domains may degrade the target-domain performance, and it is crucial to choose the proper source domains to transfer from.

* 17 pages, 4 figures 
Access Paper or Ask Questions

Word frequency and sentiment analysis of twitter messages during Coronavirus pandemic

Apr 08, 2020
Nikhil Kumar Rajput, Bhavya Ahuja Grover, Vipin Kumar Rathi

The Coronavirus pandemic has taken the world by storm as also the social media. As the awareness about the ailment increased, so did messages, videos and posts acknowledging its presence. The social networking site, Twitter, demonstrated similar effect with the number of posts related to coronavirus showing an unprecedented growth in a very short span of time. This paper presents a statistical analysis of the twitter messages related to this disease posted since January 2020. Two types of empirical studies have been performed. The first is on word frequency and the second on sentiments of the individual tweet messages. Inspection of the word frequency is useful in characterizing the patterns or trends in the words used on the site. This would also reflect on the psychology of the twitter users at this critical juncture. Unigram, bigram and trigram frequencies have been modeled by power law distribution. The results have been validated by Sum of Square Error (SSE), R2 and Root Mean Square Error (RMSE). High values of R2 and low values of SSE and RMSE lay the grounds for the goodness of fit of this model. Sentiment analysis has been conducted to understand the general attitudes of the twitter users at this time. Both tweets by general public and WHO were part of the corpus. The results showed that the majority of the tweets had a positive polarity and only about 15% were negative.

Access Paper or Ask Questions

Cross-language sentiment analysis of European Twitter messages duringthe COVID-19 pandemic

Aug 27, 2020
Anna Kruspe, Matthias Häberle, Iona Kuhn, Xiao Xiang Zhu

Social media data can be a very salient source of information during crises. User-generated messages provide a window into people's minds during such times, allowing us insights about their moods and opinions. Due to the vast amounts of such messages, a large-scale analysis of population-wide developments becomes possible. In this paper, we analyze Twitter messages (tweets) collected during the first months of the COVID-19 pandemic in Europe with regard to their sentiment. This is implemented with a neural network for sentiment analysis using multilingual sentence embeddings. We separate the results by country of origin, and correlate their temporal development with events in those countries. This allows us to study the effect of the situation on people's moods. We see, for example, that lockdown announcements correlate with a deterioration of mood in almost all surveyed countries, which recovers within a short time span.

Access Paper or Ask Questions

Fine-Grained Opinion Summarization with Minimal Supervision

Oct 17, 2021
Suyu Ge, Jiaxin Huang, Yu Meng, Sharon Wang, Jiawei Han

Opinion summarization aims to profile a target by extracting opinions from multiple documents. Most existing work approaches the task in a semi-supervised manner due to the difficulty of obtaining high-quality annotation from thousands of documents. Among them, some use aspect and sentiment analysis as a proxy for identifying opinions. In this work, we propose a new framework, FineSum, which advances this frontier in three aspects: (1) minimal supervision, where only aspect names and a few aspect/sentiment keywords are available; (2) fine-grained opinion analysis, where sentiment analysis drills down to the sub-aspect level; and (3) phrase-based summarization, where opinion is summarized in the form of phrases. FineSum automatically identifies opinion phrases from the raw corpus, classifies them into different aspects and sentiments, and constructs multiple fine-grained opinion clusters under each aspect/sentiment. Each cluster consists of semantically coherent phrases, expressing uniform opinions towards certain sub-aspect or characteristics (e.g., positive feelings for ``burgers'' in the ``food'' aspect). An opinion-oriented spherical word embedding space is trained to provide weak supervision for the phrase classifier, and phrase clustering is performed using the aspect-aware contextualized embedding generated from the phrase classifier. Both automatic evaluation on the benchmark and quantitative human evaluation validate the effectiveness of our approach.

Access Paper or Ask Questions

"Thought I'd Share First": An Analysis of COVID-19 Conspiracy Theories and Misinformation Spread on Twitter

Dec 14, 2020
Dax Gerts, Courtney D. Shelley, Nidhi Parikh, Travis Pitts, Chrysm Watson Ross, Geoffrey Fairchild, Nidia Yadria Vaquera Chavez, Ashlynn R. Daughton

Background: Misinformation spread through social media is a growing problem, and the emergence of COVID-19 has caused an explosion in new activity and renewed focus on the resulting threat to public health. Given this increased visibility, in-depth analysis of COVID-19 misinformation spread is critical to understanding the evolution of ideas with potential negative public health impact. Methods: Using a curated data set of COVID-19 tweets (N ~120 million tweets) spanning late January to early May 2020, we applied methods including regular expression filtering, supervised machine learning, sentiment analysis, geospatial analysis, and dynamic topic modeling to trace the spread of misinformation and to characterize novel features of COVID-19 conspiracy theories. Results: Random forest models for four major misinformation topics provided mixed results, with narrowly-defined conspiracy theories achieving F1 scores of 0.804 and 0.857, while more broad theories performed measurably worse, with scores of 0.654 and 0.347. Despite this, analysis using model-labeled data was beneficial for increasing the proportion of data matching misinformation indicators. We were able to identify distinct increases in negative sentiment, theory-specific trends in geospatial spread, and the evolution of conspiracy theory topics and subtopics over time. Conclusions: COVID-19 related conspiracy theories show that history frequently repeats itself, with the same conspiracy theories being recycled for new situations. We use a combination of supervised learning, unsupervised learning, and natural language processing techniques to look at the evolution of theories over the first four months of the COVID-19 outbreak, how these theories intertwine, and to hypothesize on more effective public health messaging to combat misinformation in online spaces.

Access Paper or Ask Questions