实证中,Loughran and McDonald(2014a)展示了很多不同的度量可读性的方法:年报文件的文本的大小的自然对数(the natural log of the text document 10-K file size in megabytes),单词的共同性(commonality of words),专业术语的数量(count of jargon words),文件中的单词数(number of words in the document)。...
The Power of Words: Understanding Financial Sentiment Analysis Using Loughran and McDonald’s Word List In today’s fast-paced market, investors and traders are always on the lookout for the next big thing that can give them an edge. One such tool that has gained popularity over the years ...
We demonstrate that transformer-aided explainable lexicons can improve the vocabulary coverage of the benchmark Loughran-McDonald (LM) lexicon and outperform it in sentiment analysis of financial datasets. Such lexicons are also significantly more efficient in terms of model speed and size compared ...