.
.
Read More
NLP research notes
JS DECODER
[JS]Decoder is an online enconding/decoding tool for common web methods. All text entered is processed locally and not transfered to the server.
- Base64 encoding is commonly used for transforming binary files into a format which is easilly handled in intransports which are not normally binary safe (such as email). It is also used as an obfuscation method in some malware. Base64 encoded strings can often be identified by the presence of trailing equal '=' signs, which as used to pad strings to the correct length for decoding.
- URLEncoding ensures that text strings are safe for inclusion in URLs by transforming problematic characters (such as /:#? and spaces) to their hexadeximal representation (such as %2f). Text string encoded this way can safely be included in URLs (up to the length limitation).
- Rot13 (Rotate 13) is an early (and highly insecure) 'encryption' technique which rotates all letters by 13 positions. The use of 13 is significant as decoding only requires reapplication of the same method. Other key rotation lengths produce a similar result however they require a different rotation length to return to the plain text.
- MD5,SHA1 & others, are cryptographic hash functions which are used for securing passwords, integrity validation and proof of pocession.
- Hex2Bin & Bin2Hex converts hexidecimal strings to their binary equivilant (and back). NOTE: this may not display well in the next box, however the next function works as expected
.
Read More
Comparison of emotion lexicons
.
A:
Although the research of emotion detection from social media grows, not much research has been focused on the construction of emotion lexicon, which plays an important role on emotion classification.
In this paper, we compare frequently used emotion lexicons EmoSenticNet (ESN) , and National Research Council Canada (NRC) as well as relatively newer emotion lexicons DepecheMood (DPM) , and Topic based DepecheMood (TDPM).
Comparisons are performed in terms of size, type and kind of words used to construct lexicons, The lexicons, and some of their subset combinations, are evaluated via emotion classification process on Semeval-2007 test dataset.
Experiments provide detailed comparison of the effects of lexicons on emotion classification process.
.
K:
emotion lexicon; lexicon comparison; emotion classification;
.
P:
https://ieeexplore.ieee.org/document/7753440
.
S:
.
R:
https://www.researchgate.net/publication/310808474_Comparison_of_emotion_lexicons
.
G:
https://app.razzi.my/findgref?gid=1G9ULEfe0d9UqIDEEDpFtcxHddeCvw-ZV
.
How Many Types Are There For Neural Network Architecture?
"Neural Network Zoo" Chart
.
REFERENCE:
Van Veen, F. & Leijnen, S. (2019). The Neural Network Zoo.
.
A neural network is actually just a mathematical function. You enter a vector of values, those values get multiplied by other values, and a value or vector of values is output.
.
They are very useful in problem domains where there is no known function for approximating the given features (or inputs) to their outputs (classification or regression). One example would be the weather - there are lots of features to the weather - type, temperature, movement, cloud cover, past events, etc - but nobody can say exactly how to calculate what the weather will be 2 days from now. A neural network is a function that is structured in a way that makes it easy to alter its parameters to approximate weather predication based on features.
.
Therefore, Neural Network is a function and has a structure suited to "learning". One would take the past five years of weather data - complete with the features of the weather and the condition of the weather 2 days in the future, for every day in the past five years. The network weights (multiplying factors which reside in the edges) are generated randomly, and the data is run through. For each prediction, the NN will output values that are incorrect.
.
Using a learning algorithm based in calculus, such as back-propagation, one can use the output error values to update all the weights in the network. After enough runs through the data, the error levels will reach some lowest point. The goal is to stop the learning algorithm when error levels are at a best point. The network is then fixed and at this point it is just a mathematical function that maps input values into output values just like any old equation.
.
REFERENCE:
.
Semantic Orientation-Based Approach for Sentiment Analysis
.
A:
Two types of techniques have been used in the literature for semantic orientation-based approach for sentiment analysis, viz., (i) corpus based and (ii) dictionary or lexicon or knowledge based.
In this chapter, we explore the corpus-based semantic orientation approach for sentiment analysis.
Corpus-based semantic orientation approach requires large dataset to detect the polarity of the terms and therefore the sentiment of the text.
The main problem with this approach is that it relies on the polarity of the terms that have appeared in the training corpus since polarity is computed for the terms that are in the corpus.
This approach has been explored well in the literature due to the simplicity of this approach [29, 120].
This approach initially mines sentiment-bearing terms from the unstructured text and further computes the polarity of the terms.
Most of the sentiment-bearing terms are multi-word features unlike bag-of-words, e.g., “good movie,” “nice cinematography,” “nice actors,” etc.
Performance of semantic orientation-based approach has been limited in the literature due to inadequate coverage of the multi-word features.
.
C:
Agarwal, B., & Mittal, N. (2016). Semantic Orientation-Based Approach for Sentiment Analysis.
.
K:
Sentiment Analysis, Multi-word Features, Semantic Orientation, Seed Word List, Mutual Information Method
.
P:
https://link.springer.com/chapter/10.1007/978-3-319-25343-5_6
.
S:
.
R:
.
G:
https://app.razzi.my/findgref?gid=1sICPEHZfxAmrC9Xse2vjyKQ7-vImSElF
Read More
JS Hint - A Static Code Analysis Tool for JavaScript
.
JSHint, A Static Code Analysis Tool for JavaScript
.
The project aims to help JavaScript developers write complex programs without worrying about typos and language gotchas.
Any code base eventually becomes huge at some point, so simple mistakes — that would not show themselves when written — can become show stoppers and add extra hours of debugging. So, static code analysis tools come into play and help developers spot such problems. JSHint scans a program written in JavaScript and reports about commonly made mistakes and potential bugs. The potential problem could be a syntax error, a bug due to an implicit type conversion, a leaking variable, or something else entirely.
Only 15% of all programs linted on jshint.com pass the JSHint checks. In all other cases, JSHint finds some red flags that could've been bugs or potential problems.
Please note, that while static code analysis tools can spot many different kind of mistakes, it can't detect if your program is correct, fast or has memory leaks. You should always combine tools like JSHint with unit and functional tests as well as with code reviews.
.
Read More
Subscribe to:
Posts (Atom)