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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Sentiment": models, code, and papers

Look inside. Predicting stock prices by analysing an enterprise intranet social network and using word co-occurrence networks

May 25, 2021
A. Fronzetti Colladon, G. Scettri

This study looks into employees' communication, offering novel metrics which can help to predict a company's stock price. We studied the intranet forum of a large Italian company, exploring the interactions and the use of language of about 8,000 employees. We built a network linking words included in the general discourse. In this network, we focused on the position of the node representing the company brand. We found that a lower sentiment, a higher betweenness centrality of the company brand, a denser word co-occurrence network and more equally distributed centrality scores of employees (lower group betweenness centrality) are all significant predictors of higher stock prices. Our findings offers new metrics that can be helpful for scholars, company managers and professional investors and could be integrated into existing forecasting models to improve their accuracy. Lastly, we contribute to the research on word co-occurrence networks by extending their field of application.

* International Journal of Entrepreneurship and Small Business 36(4), 378-391 (2019) 

  Access Paper or Ask Questions

SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian

Apr 15, 2021
Nasrin Taghizadeh, Ehsan Doostmohammadi, Elham Seifossadat, Hamid R. Rabiee, Maedeh S. Tahaei

We have released Sina-BERT, a language model pre-trained on BERT (Devlin et al., 2018) to address the lack of a high-quality Persian language model in the medical domain. SINA-BERT utilizes pre-training on a large-scale corpus of medical contents including formal and informal texts collected from a variety of online resources in order to improve the performance on health-care related tasks. We employ SINA-BERT to complete following representative tasks: categorization of medical questions, medical sentiment analysis, and medical question retrieval. For each task, we have developed Persian annotated data sets for training and evaluation and learnt a representation for the data of each task especially complex and long medical questions. With the same architecture being used across tasks, SINA-BERT outperforms BERT-based models that were previously made available in the Persian language.

  Access Paper or Ask Questions

NITS-VC System for VATEX Video Captioning Challenge 2020

Jun 07, 2020
Alok Singh, Thoudam Doren Singh, Sivaji Bandyopadhyay

Video captioning is process of summarising the content, event and action of the video into a short textual form which can be helpful in many research areas such as video guided machine translation, video sentiment analysis and providing aid to needy individual. In this paper, a system description of the framework used for VATEX-2020 video captioning challenge is presented. We employ an encoder-decoder based approach in which the visual features of the video are encoded using 3D convolutional neural network (C3D) and in the decoding phase two Long Short Term Memory (LSTM) recurrent networks are used in which visual features and input captions are fused separately and final output is generated by performing element-wise product between the output of both LSTMs. Our model is able to achieve BLEU scores of 0.20 and 0.22 on public and private test data sets respectively.

* 4 pages, 1 figure 

  Access Paper or Ask Questions

SubjQA: A Dataset for Subjectivity and Review Comprehension

Apr 29, 2020
Johannes Bjerva, Nikita Bhutani, Behzad Golshan, Wang-Chiew Tan, Isabelle Augenstein

Subjectivity is the expression of internal opinions or beliefs which cannot be objectively observed or verified, and has been shown to be important for sentiment analysis and word-sense disambiguation. Furthermore, subjectivity is an important aspect of user-generated data. In spite of this, subjectivity has not been investigated in contexts where such data is widespread, such as in question answering (QA). We therefore investigate the relationship between subjectivity and QA, while developing a new dataset. We compare and contrast with analyses from previous work, and verify that findings regarding subjectivity still hold when using recently developed NLP architectures. We find that subjectivity is also an important feature in the case of QA, albeit with more intricate interactions between subjectivity and QA performance. For instance, a subjective question may or may not be associated with a subjective answer. We release an English QA dataset (SubjQA) based on customer reviews, containing subjectivity annotations for questions and answer spans across 6 distinct domains.

  Access Paper or Ask Questions

Contextual Recurrent Units for Cloze-style Reading Comprehension

Nov 14, 2019
Yiming Cui, Wei-Nan Zhang, Wanxiang Che, Ting Liu, Zhipeng Chen, Shijin Wang, Guoping Hu

Recurrent Neural Networks (RNN) are known as powerful models for handling sequential data, and especially widely utilized in various natural language processing tasks. In this paper, we propose Contextual Recurrent Units (CRU) for enhancing local contextual representations in neural networks. The proposed CRU injects convolutional neural networks (CNN) into the recurrent units to enhance the ability to model the local context and reducing word ambiguities even in bi-directional RNNs. We tested our CRU model on sentence-level and document-level modeling NLP tasks: sentiment classification and reading comprehension. Experimental results show that the proposed CRU model could give significant improvements over traditional CNN or RNN models, including bidirectional conditions, as well as various state-of-the-art systems on both tasks, showing its promising future of extensibility to other NLP tasks as well.

* 10 pages 

  Access Paper or Ask Questions

Event Representation Learning Enhanced with External Commonsense Knowledge

Sep 09, 2019
Xiao Ding, Kuo Liao, Ting Liu, Zhongyang Li, Junwen Duan

Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction. On the other hand, events extracted from raw texts lacks of commonsense knowledge, such as the intents and emotions of the event participants, which are useful for distinguishing event pairs when there are only subtle differences in their surface realizations. To address this issue, this paper proposes to leverage external commonsense knowledge about the intent and sentiment of the event. Experiments on three event-related tasks, i.e., event similarity, script event prediction and stock market prediction, show that our model obtains much better event embeddings for the tasks, achieving 78% improvements on hard similarity task, yielding more precise inferences on subsequent events under given contexts, and better accuracies in predicting the volatilities of the stock market.

* arXiv admin note: text overlap with arXiv:1711.07611, 1805.02474 by other authors 

  Access Paper or Ask Questions

Transforming Delete, Retrieve, Generate Approach for Controlled Text Style Transfer

Aug 25, 2019
Akhilesh Sudhakar, Bhargav Upadhyay, Arjun Maheswaran

Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach to rewriting sentences to a target style in the absence of parallel style corpora. GST leverages the power of both, large unsupervised pre-trained language models as well as the Transformer. GST is a part of a larger `Delete Retrieve Generate' framework, in which we also propose a novel method of deleting style attributes from the source sentence by exploiting the inner workings of the Transformer. Our models outperform state-of-art systems across 5 datasets on sentiment, gender and political slant transfer. We also propose the use of the GLEU metric as an automatic metric of evaluation of style transfer, which we found to compare better with human ratings than the predominantly used BLEU score.

* 11 pages, 6 Tables, 2 Figures, Accepted at 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP - 2019) 

  Access Paper or Ask Questions

Unsupervised Neural Multi-document Abstractive Summarization

Oct 12, 2018
Eric Chu, Peter J. Liu

Abstractive summarization has been studied using neural sequence transduction methods with datasets of large, paired document-summary examples. However, such datasets are rare and the models trained from them do not generalize to other domains. Recently, some progress has been made in learning sequence-to-sequence mappings with only unpaired examples. In our work, we consider the setting where there are only documents and no summaries provided and propose an end-to-end, neural model architecture to perform unsupervised abstractive summarization. Our proposed model consists of an auto-encoder trained so that the mean of the representations of the input documents decodes to a reasonable summary. We consider variants of the proposed architecture and perform an ablation study to show the importance of specific components. We apply our model to the summarization of business and product reviews and show that the generated summaries are fluent, show relevancy in terms of word-overlap, representative of the average sentiment of the input documents, and are highly abstractive compared to baselines.

* preprint 

  Access Paper or Ask Questions

Social Emotion Mining Techniques for Facebook Posts Reaction Prediction

Dec 08, 2017
Florian Krebs, Bruno Lubascher, Tobias Moers, Pieter Schaap, Gerasimos Spanakis

As of February 2016 Facebook allows users to express their experienced emotions about a post by using five so-called `reactions'. This research paper proposes and evaluates alternative methods for predicting these reactions to user posts on public pages of firms/companies (like supermarket chains). For this purpose, we collected posts (and their reactions) from Facebook pages of large supermarket chains and constructed a dataset which is available for other researches. In order to predict the distribution of reactions of a new post, neural network architectures (convolutional and recurrent neural networks) were tested using pretrained word embeddings. Results of the neural networks were improved by introducing a bootstrapping approach for sentiment and emotion mining on the comments for each post. The final model (a combination of neural network and a baseline emotion miner) is able to predict the reaction distribution on Facebook posts with a mean squared error (or misclassification rate) of 0.135.

* 10 pages, 13 figures and accepted at ICAART 2018. (Dataset:

  Access Paper or Ask Questions

Learning to Compose Task-Specific Tree Structures

Nov 21, 2017
Jihun Choi, Kang Min Yoo, Sang-goo Lee

For years, recursive neural networks (RvNNs) have been shown to be suitable for representing text into fixed-length vectors and achieved good performance on several natural language processing tasks. However, the main drawback of RvNNs is that they require structured input, which makes data preparation and model implementation hard. In this paper, we propose Gumbel Tree-LSTM, a novel tree-structured long short-term memory architecture that learns how to compose task-specific tree structures only from plain text data efficiently. Our model uses Straight-Through Gumbel-Softmax estimator to decide the parent node among candidates dynamically and to calculate gradients of the discrete decision. We evaluate the proposed model on natural language inference and sentiment analysis, and show that our model outperforms or is at least comparable to previous models. We also find that our model converges significantly faster than other models.

* AAAI 2018 

  Access Paper or Ask Questions