At present, the main methods for judging sentiments include building an inventory of lexical categories, using dictionaries for analysis of lexical categories, and machine learning.
With regards to research about investors' sentiments based on Internet big data, the main methods of sentiments analysis include building an inventory of lexical categories, using dictionaries for analysis of lexical categories, and machine learning.
(2) As for research about investors' sentiments on the basis of Internet big data, the main methods of sentiment analysis include building an inventory of lexical categories, using dictionaries for analysis of lexical categories, and machine learning.
To address this issue, Loughran and McDonald (2011) developed an inventory of lexical categories that is more appropriate for financial research.
For analytical purposes, Bartov et al. (2015) constructed four tendency indicators of market sentiments using the enhanced Naive Bayes classifier, Harvard-IV dictionand, and inventory of lexical categories by Loughran and McDonald (2011).
A large number of sentiment-type keywords are selected from the sample text to build an inventory of lexical categories, which are used as the judgment criterion for classification of all the text (Nan 2015; Shen et al. 2013; Xu and Chen 2016; Zhang et al. 2011a).
In the field of financial research, the main distinction between these two methods lies in the sources of keywords: the source of the first method is text information from the samples, whereas the sources for the second method are actual dictionaries or inventories of lexical categories developed on the basis of dictionaries.
Participants at the meeting shared existing work on lexical analysis and concept inventories, participated in technology demonstrations and workshops, and discussed research goals.
The exclusion criteria were presence of brain lesions, ascertained with brain imaging studies; severe systemic diseases or depression; severe behavioral symptoms, evaluated with the Neuropsychiatric Inventory 28 questionnaire; and serious lexical-semantic deficits that may interfere with the rehabilitation, assessed with the verbal naming test score ≥2 standard deviations below normal values.
Language cues can be categorized according to their level of knowledge abstraction as acoustic (spectrum, phone inventory), prosodic (duration, pitch, intonation), phonotactic (sequence of sounds), lexical (vocabulary, morphology), and syntax (phrases, grammar) [3],[4].
