=Paper= {{Paper |id=Vol-3105/paper31 |storemode=property |title=Sentiment Analysis: Using Detrended Fluctation Analysis of EEG Signals in Natural Reading |pdfUrl=https://ceur-ws.org/Vol-3105/paper31.pdf |volume=Vol-3105 |authors=Boi Mai Quach,Cathal Gurrin,Graham Healy |dblpUrl=https://dblp.org/rec/conf/aics/QuachGH21 }} ==Sentiment Analysis: Using Detrended Fluctation Analysis of EEG Signals in Natural Reading== https://ceur-ws.org/Vol-3105/paper31.pdf

Sentiment Analysis: Using Detrended Fluctation
Analysis of EEG Signals in Natural Reading

Boi Mai Quach1 , Cathal Gurrin1 , and Graham Healy1

Dublin City University, Ireland
mai.quach3@mail.dcu.ie
{cathal.gurrin,graham.healy}@dcu.ie

Abstract. While Natural Language Processing (NLP) techniques can
be used to identify sentiment in text, information sources such as the neu-
ral signals of a reader are typically not incorporated into the process. In
this paper, we investigated whether measures extracted from Electroen-
cephalography (EEG) signals during reading could be used to identify
the sentiment of sentences. Our study used the ZuCo dataset which con-
tained 18 channels of EEG collected from 10 native English speakers as
they read 400 sentences. Each sentence belonged to a positive, negative
or neutral sentiment class. We show how Detrended Fluctuation Analy-
sis (DFA), an extension to chaotic systems fluctuation analysis, can be
used to identify differences and changes in human EEG for reading texts
with different sentiments. Based on DFA, on each time scale, we found
that the left and right occipital electrodes had the greatest activation
between sentiment conditions, and the EEG at electrodes over temporal-
frontal scalp sites showed a significant change over many frequency bands
for texts of different sentiment. Additionally, we also compared DFA to
descriptive statistics to show that DFA is a useful technique for EEG
analysis.

Keywords: EEG · DFA · sentiment · statistics · electrode.

1 Introduction

Sentiment analysis is a branch of Natural Language Processing (NLP) that is
used to indicate and understand opinions expressed in written language. One
area where this is frequently used is on the reviews that can be found in many
common publicly available datasets e.g. Stanford Sentiment Treebank[18], Ama-
zon product data, IMDB Movie Reviews Dataset, Twitter US Airline Sentiment[3].
However, there are many challenges when using sentiment analysis approaches.
Many questions have been raised regarding how human language works when
people directly read sentences or documents that contain sentiment.
The next stage in the development of NLP will involve the incorporation of
different modalities instead of concentrating only on text-based data [10,1]. In
recent years, using EEG (Electroencephalography) signals in linguistic research,
especially in normal reading has enabled numerous insights [11,7,9,19]. However,

Copyright 2021 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)
2 Boi Mai Quach et al.

although combining neural signals with artificial intelligence methods may seem
tempting, it is still a challenging task because the signals often contain noise,
artifacts, or interference [16]. In order to achieve a better understanding of how
to use EEG signals in natural reading tasks, and to combine them with NLP
methods to get closer to human-level language comprehension, we need novel
approaches to combine EEG (Electroencephalography) signals with sentiment
analysis. Previous studies have reported that EEG signals are nonlinear, self-
affine, and non-stationary [4,22]. Thus, traditional statistical methods of EEG
analysis (e.g. Fourier transform) may fail to capture important properties of
the signals since these techniques are intended for stationary signals with inde-
pendent frequencies [12]. In this sense, Detrended Fluctuation Analysis (DFA)
has been shown to be useful for non-stationary time series [5], especially brain
activity signals.
There are many studies that have successfully applied DFA for EEG signal
analysis. Zebende et al[20] applied DFA to analyze four different channels from
a total of 64 with three time scales corresponding to frequencies smaller than
40Hz in the motor/imaginary human task. Similarly, Filho et al.[13] used DFA
to analyze 22 channels of EEG in a reading task performed by one subject that
had been trained before an experiment while the other participants were not.
They also achieved clear differences in 11 channels between two subjects by using
DFA for four frequency (f) bands including δ, θ, α, and β (f < 30Hz).
In this paper we used the Zurich Cognitive Language Processing Corpus
(ZuCo) dataset [7]. This is a publicly available dataset that provides simultane-
ous EEG and eye-tracking data for natural sentence reading to support aspect-
based sentiment analysis. In the original paper for this dataset, they consider
EEG signals based on four frequency bands including γ, β, α, and θ. Other
studies that used this dataset have typically focused on decoding and combining
EEG signals with text-based data to address the sentiment analysis task [6,14].
At present there is no study that identifies which EEG electrode locations might
be important for sentiment analysis. In order to answer this question, we applied
both the traditional technique (descriptive statistics) and DFA. Along with the
main question, with the DFA method, we can observe the changes of each elec-
trode and compare them to each other for specific frequencies that cannot be
explained by the descriptive statistics.
The rest of the paper is structured as follows. First, we provide a dataset
description and describe the data preprocessing. This is followed by the method-
ology that describes the procedures of using descriptive statistics and DFA.
Following this, Section 4 illustrates main results and analysis. The conclusion is
then presented in Section 5.

2 Dataset and Processing
The ZuCo dataset1 was first released for reading tasks in this paper [7]. It consists
of EEG measures co-registered to eye fixations for participants reading text. All
1
https://osf.io/q3zws/
Using Detrended Fluctation Analysis of EEG Signals in Natural Reading 3

participants were presented with 400 sentences describing movie reviews that
belonged to one of three types of sentiment categories i.e. positive, negative,
and neutral. These sentences in the ZuCo dataset were selected randomly from
the Stanford Sentiment Treebank (SST) [18]. The SST has been used in the
task of sentiment analysis in which algorithms must analyze and predict the
sentiment of a sentence. There were 123 negative, 137 neutral, and 140 positive
sentences used for subjects in the ZuCo dataset, accounting for approximately
4% of the SST dataset. For the sentiment task, a control pad was used to switch
to the next sentence and the subjects had to indicate the correct sentiment.
Unlike Rapid Serial Visual Representation (RSVP) [8] in which each word is
displayed independently at a uniform speed, the experimental setup ensured
natural reading behaviours. This means each of the subjects could read each
sentence at various speeds and could freely reread words or even the entire
sentence.
During normal reading, the perceived sentiment of text can be affected by
surroundings, domain knowledge or interests. The ZuCo dataset was recorded
in a controlled manner in order to mitigate these influences. Similarly, domain
knowledge or interests of the subject can impact their perceived sentiment of text
i.e. if people read a text and its content is outside their domain of expertise or is
not a topic of interest for them, the sentiment they choose for the sentence could
be influenced. The sentences that were used in the ZuCo dataset experiment
were selected from the Stanford Sentiment Treebank, a corpus with fully labeled
parse trees from movie reviews that should be suitable for everyone. Besides, the
average number of seconds a subject spends per sentence is around 5.52. With
the reading speed and the content of movie reviews, reader’s sentiment associated
with their domain knowledge or interests should not have a significant effect i.e.
the sentiment they choose for each sentence.
The ZuCo dataset includes both raw and preprocessed EEG data using Au-
tomagic (version: 1.4.6)2 . There are 105 channels of EEG, with an additional 9
channels that are used for EOG artifact removal, as well as other channels corre-
sponding to locations on the neck and face that were excluded from the dataset
due to noise. The procedure for EEG preprocessing using Automagic is described
in [7]. In this study, we extracted the final data from the preprocessing step and
built a pipeline to get 105 channels of EEG that were band-pass filtered between
a frequency range from 4 Hz to 50 Hz. Given that EEG channels that correspond
to nearby electrode sites tend to be correlated, not all of the 105 channels were
analysed. If we analyzed all 105 channels, this would be cumbersome for anal-
ysis and visualization. Hence we chose a representative selection of electrodes.
[17], they used 8 channels Fp1, Fp2, F7, F8, T3, T4, F3 and F4 according to
the 10-20 system to implement the sentiment classification task. Another paper
also assessed EEG signals for emotion recognition but they implemented their
experiment on visual-based data [21]. However, in terms of emotion recognition,
similar to our task, they concluded that FP2, O2, T7, T8 channels contained sig-
2
The whole preprocessing can be found at https://github.com/methlabUZH/
automagic
4 Boi Mai Quach et al.

nificant activity related to sentiment recognition. Most previous studies use the
10-20 International System for electrode placement, however, the ZuCo dataset
was collected on a 128-channel EEG Geodesic Hydrocel system that does not
perfectly align with this electrode placement system. Electrode Cz was used as
a reference during data recording, where after the experiment the data was re-
referenced to a common average reference. In this paper, we use 18 channels of
EEG with nearly the same locations as the International 10-20 System (shown
in Figure 1 for convenience of analysis and interpretation. These electrodes are
symmetrical with respect to the midline on the scalp covering regions above the
left and right frontal lobes, parietal lobes, occipital lobes, temporal lobes, and
central region.

(a) (b)

Fig. 1. Electrodes position on the scalp in terms of the (a) 128-channel EEG Geodesic
Hydrocel system (b) International 10-20 protocol

The average time for each sentiment sentence is approximately 5.52 seconds
while the sentence that accounted for the longest time to read was nearly 14.8 sec-
onds and the shortest one was around 1.1 seconds. For each sentiment sentence,
we used EEG signals recorded from 19 electrodes for 10 subjects. Therefore, we
had 23,370, 26,030, and 26,600 epochs according to each sentiment condition.

3 Methodology

3.1 Statistical techniques

There are two types of statistical techniques that were used to analyse EEG sig-
nals during the sentiment reading task. Firstly, descriptive statistics were applied
in order to have an overview of all signals from collected channels via statistical
measures such as mean, standard deviation, skewness, and kurtosis. Also, DFA
is used to find differences between any two considered channels for three groups
of sentiment sentences. According to Peng’s work [15], mathematically DFA can
be decomposed and implemented in the following steps:
Using Detrended Fluctation Analysis of EEG Signals in Natural Reading 5

Step 1: Calculate the average cumulative sum y(k) of an EEG signal (xi ), with
i = 1, 2, ..., N −1, N , and N the numberPof samples. From this definition,
k
we achieve the integrated series y(k) = i=1 (xi −x), where x is the mean
value and k = 1, 2, ..., N − 1, N .
Step 2: Subdivide the averaged cumulative sum yk in n samples and for each sub-
sample compute a least square linear fitting yn (k). Repeat this process
at different scales, namely from dividing the signal in many n time scales.
Step 3: Compute the detrended fluctuation F (n) as the root-mean-square devi-
ation between the averaged cumulative sum y(k) and the fitting yn (k),
at each scale: v
u
u1 X N
F (n) = t (y(k) − yn (k))2 (1)
N
k=1
Step 4: Express ∆logFDF A as a log function with the number of n samples to
compare two signals.
EEG signals can be analysed in terms of their power spectral density, ampli-
tude, shape, and position. Power spectral density is a fundamental method to
determine the differences in rhythms. Hence, for this analysis, we analyzes the
EEG signals in terms of four different frequency bands according to common
analysis frequency bands as follows: θ (4-8Hz), α (8.5-13Hz), β (13.5-30Hz), and
γ (30.5-49.5Hz). Based on these frequency bands and sampling rate of 500Hz
(∆t = 0.002), four ranges of window size from 10 to 125 corresponding to time
scale from 0.02s to 0.25s are used for the DFA method. This is detailed in Table
1.

Table 1. Relations between n, time scale (s) and the frequency (Hz)

Bands Frequency n∆t n
γ-wave 31.25 - 50.00 0.020 - 0.032 10 - 16
β-wave 13.16 - 31.25 0.032 - 0.076 16 - 38
α-wave 8.060 - 13.16 0.076 - 0.124 38 - 62
θ-wave 4.000 - 8.060 0.124 - 0.250 62 - 125

If the FDF A value of a channel is higher than other channels for a particular
time scale, we refer to that channel as being more active. If we compare FDF A
values between two or more channels, comparing FDF A directly is not suitable as
it will fail to show differences due to the small differences between channels. Thus,
the ∆logFDF A function is used as this method has been shown to be successful
by other authors[20] in the analysis of the time series of motor/imaginary EEG.
Where Fd is FDF A value of the most active channel and Fx is FDF A value of
electrode x, the formula for this function becomes:
∆logFDF A := logFd − logFx (2)
From ∆logFDF A , the relationship between two electrodes can be analyzed as
follows:
6 Boi Mai Quach et al.

i: If ∆logFDF A > 0, the difference in the log-amplitude of DFA between the
most active channel and electrode x is larger.
ii: If ∆logFDF A = 0, the difference in the log-amplitude of DFA between the
most active channel and electrode x is zero.
iii: If ∆logFDF A < 0, the difference in the log-amplitude of DFA between the
most active channel and electrode x is smaller.

4 Results and Analysis

4.1 Descriptive statistics

We calculated statistical measures of entire sentiment sentences for all subjects
at the sentence level for 18 channels of EEG. In Figure 2, time-series EEG at
each electrode is considered in three sentiment conditions, and summarised by
mean, standard deviation, skewness, and kurtosis. The calculated statistical mea-
sures do not show clear differences between negative (blue circle), neutral(orange
circle), and positive (green circle) in the EEG for sentiment conditions when
analysed across all subjects. A one-way ANOVA was used to evaluate whether
there is any difference between three sentiment conditions across all channels
for each subject with 95% confidence intervals. P-values for mean, standard de-
viation, skewness, and kurtosis were 0.070, 0.995, 0.901, and 0.169 respectively.
Thus, there was no statistically significant difference in all statistical measures
according to three sentiment conditions (p − values > 0.05). With regard to
the mean measure, all channels approach zero. For skewness measures, since all
values for 18 channels were between -0.5 and 0.5, they were fairly symmetrical.
Kurtosis tells us the tails of distributions of the considered signals. According
to the kurtosis plot, all values are smaller than 3, which means the distributions
are platykurtic i.e. the distribution is shorter, tails are thinner than the nor-
mal distribution. The low kurtosis values also indicate that all electrodes had a
lack of outliers thus being amenable for analysis. E70 had the highest standard
deviation in three classes.

4.2 Detrended Fluctuation Analysis

To begin, we use a one-way ANOVA to test whether there is any significant
difference between FDF A of each electrode over ten subjects in terms of three
sentiment conditions. The distribution of p values is 0.55 ± 0.27. Since our p
values are all larger than 0.05, we do not have a statistically significant differ-
ence between sentiment conditions on a per participant-electrode combination.
Therefore, we can compute FDF A values without taking subjects into account.
The results of the FDF A values potentially reflect the discrimination between
different electrode signals. In raw data, we cannot determine which one has the
greatest amplitude over others. However, based on FDF A , for most of the time
scales, the FDF A value of E70 is always higher than that of other channels. This
indicates that E70 is the most active channel. Considering all time scales, the
Using Detrended Fluctation Analysis of EEG Signals in Natural Reading 7

Fig. 2. Descriptive Statistical for EEG based on sentiment classes

FDF A values of E70 and E83 are not much different for each condition. Therefore,
we need to implement the next step to calculate ∆logFDF A to identify the
time scale having the greatest difference between E70 and E83 as well as other
electrodes.
All computed ∆logFDF A are illustrated in Figure 3. In this figure, there
are four clusters that depend on the distance from electrode positions to the
occipital electrodes since we calculate the difference between E70 (left of occipital
lobe) and others. That also explains the reason why ∆logFDF A becomes smaller
if an electrode channel is near the electrode E70. Based on the conditions of
∆logFDF A , for ∆logFDF A > 0, we find that the E70 competes with E83 as
the most active channel in a half of β band frequency and in both γ while E83
replaces this for the time scale n > 30 or frequency f < 16.67Hz (∆logFDF A <
0). Additionally, ∆logFDF A values of E33 (red line) and E122 (brown line)
at electrodes at temporal-frontal scalp sites are significantly different for the 3
sentiment conditions. Therefore, we visualize ∆logFDF A between two channels
separately to observe their characteristics.
Looking at Figure 4, ∆logFDF A < 0 since the low β wave with f < 16Hz, E83
has become the most active channel instead of E70 in this case. However, what
stands out from this figure is that negative sentences (blue) appear to change
in the most active channel when frequency is larger (n is smaller) than others
whereas this alternative occurs for both neutral (orange) and positive (green)
at the same frequency. According to the graph, it is difficult to determine the
difference between three conditions represented by three time series. In other
to verify these differences, a one-way ANOVA is used, where we find out there
is a significant difference in the ∆logFDF A of both channels in α (p − value =
0.0075 < 0.05) and θ (p − value = 0.0026 < 0.05) frequencies for the 3 sentiment
conditions.
8 Boi Mai Quach et al.

Fig. 3. Log FDF A difference between E70 and other channels

Fig. 4. Log FDF A difference between E70 and E83

Figure 5 indicates the changes in ∆logFDF A of the E33 and the E122 for
three conditions over a number of time scales. Generally, we observed that the
value of ∆logFDF A are apparently different. Using ∆logFDF A which is a method
to show the difference in logFDF A of two electrodes is actually effective in this
case. Moreover, we also used a one-way ANOVA to test a confidence interval
for this difference. P-values of all band frequency for three types of conditions
were 2.10−14 , 6.2.10−21 , 6.8.10−24 , and 5.7.10−19 for γ, β, α, and θ that were all
smaller than 0.05, indicating we have evidence to prove that there is a difference
in logFDF A between both channels. Considering ∆logFDF A between both chan-
nels, in term of γ band frequency (n between 10 and 16) and time scale from a
Using Detrended Fluctation Analysis of EEG Signals in Natural Reading 9

part of the high β wave with 20Hz < f < 25Hz (16 < n < 20), for the negative
label, the E122 is more active than the E33 because ∆logFDF A < 0 while the
E33 is more active for both neutral and positive sentences (∆logFDF A > 0).
For the time scale n between 20 and 35 (25Hz < f < 14Hz), the E122 is more
active than the E33 for the negative and positive classes since ∆logFDF A is
smaller then zero while the E33 is more active than others for the neutral label.
During the considered time scale n from 35 to 125 (θ and α waves), because
∆logFDF A < 0 in all sentences, the E122 is more active than the E33.

Fig. 5. Log FDF A difference between E33 and E122

5 Conclusion
In this paper we analyzed brain activity patterns using DFA for aspect-based
sentiment analysis during reading. The dataset used consisted of 10 native En-
glish speakers with EEG captured as they read reviews with different sentiments.
Our analysis concentrated on three types of sentiment sentences, namely
neutral, positive, and negative. Using descriptive statistics, we did not find any
difference in EEG signals for participant-electrode combination in terms of nega-
tive, positive, and neutral sentences. We applied DFA methods and found differ-
ences and changes in 18 channels. In terms of electrode signals, the E70 channel
corresponding to an electrode placed at a left occipital scalp site, and the E83
channel corresponding to an electrode placed at a right occipital scalp site, had
the highest DFA values. Moreover, we observed that there was a significant dif-
ference in the ∆logFDF A of the E33 and the E122 for electrodes placed at left
and right temporal-frontal scalp sites for the 3 sentiment conditions.
For each frequency band, for the aforementioned channels, the majority of
the changes occurred in the beta frequency band. In this band, E83 was the most
10 Boi Mai Quach et al.

active channel instead of E70, and E122 was more active than E33. However,
every change happened in different types of beta waves (high or low beta band)
that depended on each condition. Both neutral and positive labels had relatively
similar behaviours for most of the channels. Nevertheless, there was a change
in E122 for E33 starting to appear in neutral and positive groups were the low
beta and the high beta waves, respectively.
There is scope to apply the analyses presented in this paper in aspect-based
sentiment analysis for natural reading tasks. Currently, there are two main ap-
proaches to use EEG signals with machine learning. The first one can be con-
ceived as a bottom up method that begins with engineered features and then
uses these features to build a suitable model to predict the reading task [21].
Another approach is decoding EEG signals to feed them into Deep Learning
models along with text-based data to improve the final accuracy. If we choose
the former, we need to use time series techniques or statistical methods to obtain
suitable features. For the latter, this approach is currently favoured by many re-
searchers in the NLP domain[2,14,6]. However, it can be difficult to understand
and explain the importance of electrode signals when a deep learning approach
directly learns the features in tandem with text data. Hence, our analysis, which
is the first step in a feature engineering approach, gives insight on useful fea-
tures present in EEG that could support sentiment prediction of text based on
∆logFDF A for each frequency band, and also help researchers to reduce the
number of used channels to decode EEG signals.

Acknowledgements This publication has emanated from research conducted
with the financial support of Science Foundation Ireland under Grant number
18/CRT/6183. For the purpose of Open Access, the author has applied a CC
BY public copyright licence to any Author Accepted Manuscript version arising
from this submission.

References
1. Bisk, Y., Holtzman, A., Thomason, J., Andreas, J., Bengio, Y., Chai, J., Lapata,
M., Lazaridou, A., May, J., Nisnevich, A., et al.: Experience grounds language.
arXiv preprint arXiv:2004.10151 (2020)
2. Brennan, J.R., Hale, J.T.: Hierarchical structure guides rapid linguistic predictions
during naturalistic listening. PloS one 14(1), e0207741 (2019)
3. Gamal, D., Alfonse, M., M El-Horbaty, E.S., M Salem, A.B.: Analysis of machine
learning algorithms for opinion mining in different domains. Machine Learning and
Knowledge Extraction 1(1), 224–234 (2019)
4. Gao, J., Hu, J., Tung, W.w.: Complexity measures of brain wave dynamics. Cog-
nitive neurodynamics 5(2), 171–182 (2011)
5. Hardstone, R., Poil, S.S., Schiavone, G., Jansen, R., Nikulin, V.V., Mansvelder,
H.D., Linkenkaer-Hansen, K.: Detrended fluctuation analysis: a scale-free view on
neuronal oscillations. Frontiers in physiology 3, 450 (2012)
6. Hollenstein, N., Renggli, C., Glaus, B., Barrett, M., Troendle, M., Langer, N.,
Zhang, C.: Decoding eeg brain activity for multi-modal natural language process-
ing. arXiv preprint arXiv:2102.08655 (2021)
Using Detrended Fluctation Analysis of EEG Signals in Natural Reading 11

7. Hollenstein, N., Rotsztejn, J., Troendle, M., Pedroni, A., Zhang, C., Langer, N.:
Zuco, a simultaneous eeg and eye-tracking resource for natural sentence reading.
Scientific data 5(1), 1–13 (2018)
8. Lees, S., McCullagh, P., Payne, P., Maguire, L., Lotte, F., Coyle, D.: Speed of
rapid serial visual presentation of pictures, numbers and words affects event-related
potential-based detection accuracy. IEEE Transactions on Neural Systems and
Rehabilitation Engineering 28(1), 113–122 (2019)
9. Ling, S., Lee, A.C., Armstrong, B.C., Nestor, A.: How are visual words represented?
insights from eeg-based visual word decoding, feature derivation and image recon-
struction. Human brain mapping 40(17), 5056–5068 (2019)
10. Linzen, T.: How can we accelerate progress towards human-like linguistic general-
ization? arXiv preprint arXiv:2005.00955 (2020)
11. Murphy, B., Wehbe, L., Fyshe, A.: Decoding language from the brain. Language,
cognition, and computational models pp. 53–80 (2018)
12. Nunez, P.L.: Brain, mind, and the structure of reality. Oxford University Press
(2012)
13. Oliveira Filho, F., Cruz, J.L., Zebende, G.: Analysis of the eeg bio-signals during
the reading task by dfa method. Physica A: Statistical Mechanics and its Applica-
tions 525, 664–671 (2019)
14. Oseki, Y., Asahara, M.: Design of bccwj-eeg: Balanced corpus with human elec-
troencephalography. In: Proceedings of the 12th Language Resources and Evalua-
tion Conference. pp. 189–194 (2020)
15. Peng, C.K., Buldyrev, S.V., Havlin, S., Simons, M., Stanley, H.E., Goldberger,
A.L.: Mosaic organization of dna nucleotides. Physical review e 49(2), 1685 (1994)
16. Rashid, M., Sulaiman, N., PP Abdul Majeed, A., Musa, R.M., Bari, B.S., Khatun,
S., et al.: Current status, challenges, and possible solutions of eeg-based brain-
computer interface: a comprehensive review. Frontiers in neurorobotics 14, 25
(2020)
17. Schlör, D., Zehe, A., Kobs, K., Veseli, B., Westermeier, F., Brübach, L., Roth,
D., Latoschik, M.E., Hotho, A.: Improving sentiment analysis with biofeedback
data. In: Proceedings of LREC2020 Workshop” People in language, vision and the
mind”(ONION2020). pp. 28–33 (2020)
18. Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C.D., Ng, A.Y., Potts, C.:
Recursive deep models for semantic compositionality over a sentiment treebank.
In: Proceedings of the 2013 conference on empirical methods in natural language
processing. pp. 1631–1642 (2013)
19. Sun, P., Anumanchipalli, G.K., Chang, E.F.: Brain2char: a deep architecture for
decoding text from brain recordings. Journal of Neural Engineering 17(6), 066015
(2020)
20. Zebende, G.F., Oliveira Filho, F.M., Leyva Cruz, J.A.: Auto-correlation in the
motor/imaginary human eeg signals: A vision about the fdfa fluctuations. PloS
one 12(9), e0183121 (2017)
21. Zhong, Q., Zhu, Y., Cai, D., Xiao, L., Zhang, H.: Electroencephalogram access for
emotion recognition based on a deep hybrid network. Frontiers in Human Neuro-
science 14 (2020)
22. Zorick, T., Mandelkern, M.A.: Multifractal detrended fluctuation analysis of human
eeg: preliminary investigation and comparison with the wavelet transform modulus
maxima technique. PloS one 8(7), e68360 (2013)