Numeral Understanding in Financial Tweets for Fine-Grained Crowd-Based Forecasting

@article{Chen2018NumeralUI,
  title={Numeral Understanding in Financial Tweets for Fine-Grained Crowd-Based Forecasting},
  author={Chung-Chi Chen and Hen-Hsen Huang and Yow-Ting Shiue and Hsin-Hsi Chen},
  journal={2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI)},
  year={2018},
  pages={136-143}
}
Numerals that contain much information in financial documents are crucial for financial decision making. [...] Key Method Neural network-based models with word and character-level encoders are proposed for 7-way classification and 17-way classification. We perform backtest to confirm the effectiveness of the numeric opinions made by the crowd. This work is the first attempt to understand numerals in financial social media data, and we provide the first comparison of fine-grained opinion of individual investors…Expand
aiai at the NTCIR-14 FinNum Task : Financial Numeral Tweets Fine-Grained Classification Using Deep Word and Character Embedding-Based Attention Model
This paper describes how we tackle the Fine-Grained Numeral Understanding in Financial Tweet (FinNum) task of NTCIR14. The deep word and character embedding-based attention model is proposed toExpand
Issues and Perspectives from 10,000 Annotated Financial Social Media Data
TLDR
This paper presents Fin-SoMe, a dataset with 10,000 labeled financial tweets annotated by experts from both the front desk and the middle desk in a bank’s treasury, and reveals that writer-labeled market sentiment may be a misleading label and most financial tweets provide unfounded analysis results. Expand
Overview of the NTCIR-15 FinNum-2 Task: Numeral Attachment in Financial Tweets
In FinNum task series, we focus on understanding the numeralrelated information in the financial social media data. In FinNum-2, we introduce a new task, named numeral attachment, to identify theExpand
Final Report of the NTCIR-14 FinNum Task: Challenges and Current Status of Fine-Grained Numeral Understanding in Financial Social Media Data
TLDR
The analysis of the proposed dataset in depth is provided, and the challenges of fine-grained numeral understanding in financial social media data are discussed. Expand
Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments
TLDR
This paper attempts to answer the question of whether neural network models can learn numeracy, which is the ability to predict the magnitude of a numeral at some specific position in a text description, through comprehensive experiments. Expand
TMUNLP at the NTCIR-15 FinNum-2
Machine learning methods for financial document analysis have been focusing mainly on the textual part. However, the numerical parts of these documents are also rich in information content. ThisExpand
FinNum Task : Enriched Sequence Labeling for Numeral Classification
This paper describes our submission to the NTCIR-14 FinNum Shared Task on Fine-Grained Numeral Understanding in Financial Tweets. We participate in both Subtask-1 and Subtask-2. We formulate theExpand
Numerals in Financial Narratives
Numerals are more common in financial narratives than in documents from other domains, which makes understanding numerals very important when analyzing financial documents. In this chapter, weExpand
WUST at the NTCIR-14 FinNum Task
This paper describes our system in the FinNum task at NTCIR-14, and the FinNum task is dedicated to identifying the category of a numeral from the financial social media data, i.e. tweet, forExpand
Evaluating the Rationales of Amateur Investors
TLDR
This paper proposes an approach for capturing expert-like rationales from social media platforms without the requirement of the annotated data and achieves an F1-score of 90.81%, revealing that stylistic and semantic information provides complementary cues for professional rationales. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 24 REFERENCES
SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News
This paper discusses the “Fine-Grained Sentiment Analysis on Financial Microblogs and News” task as part of SemEval-2017, specifically under the “Detecting sentiment, humour, and truth” theme. ThisExpand
News impact on stock price return via sentiment analysis
TLDR
Results show that at individual stock, sector and index levels, the models with sentiment analysis outperform the bag-of-words model in both validation set and independent testing set, and the models which use sentiment polarity cannot provide useful predictions. Expand
Twitter mood predicts the stock market
TLDR
This work investigates whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time and indicates that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others. Expand
Predicting Stock Market Behavior using Data Mining Technique and News Sentiment Analysis
TLDR
This model is based on sentiment analysis of financial news and historical stock market prices and provides better accuracy results than all previous studies by considering multiple types of news related to market and company with historical stock prices. Expand
Learning to Generate Market Comments from Stock Prices
TLDR
A novel encoder-decoder model for automatically generating market comments from stock prices that generates market comments at the fluency and the informativeness approaching human-generated reference texts. Expand
Convolutional Neural Networks for Sentence Classification
TLDR
The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors. Expand
Temporal Information Extraction
TLDR
TIE is presented, a novel, information-extraction system, which distills facts from text while inducing as much temporal information as possible, and performs global inference, enforcing transitivity to bound the start and ending times for each event. Expand
Distributed Representations of Words and Phrases and their Compositionality
TLDR
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling. Expand
An Evaluation of Security Analysts' Forecasts
Recent literature in accounting, finance, and economics often assumes that information can be processed efficiently. Among the outputs of the processing activity are the presumably appropriateExpand
Extended Named Entity Ontology with Attribute Information
TLDR
The design of a set of attributes for ENE categories is reported on using a bottom up approach to creating the knowledge using a Japanese encyclopedia, which contains abundant descriptions of ENE instances. Expand
...
1
2
3
...