This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.

/pdf/character-level-convolutional-networks-for-text-whh3tafudk.pdf

Character-level convolutional networks for text classification

Character-level Convolutional Networks for Text Classification

In this paper, we present a comprehensive review of recent developments in the application of machine learning algorithms to Spam filtering, focusing on both textual- and image-based approaches. Instead of considering Spam filtering as a standard classification problem, we highlight the importance of considering specific characteristics of the problem, especially concept drift, in designing new filters. Two particularly important aspects not widely recognized in the literature are discussed: the difficulties in updating a classifier based on the bag-of-words representation and a major difference between two early naive Bayes models. Overall, we conclude that while important advancements have been made in the last years, several aspects remain to be explored, especially under more realistic evaluation settings.

Review: A review of machine learning approaches to Spam filtering

The analytics platform at Twitter has experienced tremendous growth over the past few years in terms of size, complexity, number of users, and variety of use cases. In this paper, we discuss the evolution of our infrastructure and the development of capabilities for data mining on "big data". One important lesson is that successful big data mining in practice is about much more than what most academics would consider data mining: life "in the trenches" is occupied by much preparatory work that precedes the application of data mining algorithms and followed by substantial effort to turn preliminary models into robust solutions. In this context, we discuss two topics: First, schemas play an important role in helping data scientists understand petabyte-scale data stores, but they're insufficient to provide an overall "big picture" of the data available to generate insights. Second, we observe that a major challenge in building data analytics platforms stems from the heterogeneity of the various components that must be integrated together into production workflows---we refer to this as "plumbing". This paper has two goals: For practitioners, we hope to share our experiences to flatten bumps in the road for those who come after us. For academic researchers, we hope to provide a broader context for data mining in production environments, pointing out opportunities for future work.

http://www.datascienceassn.org/sites/default/files/Scaling%20Big%20Data%20Mining%20Infrastructure%20-%20The%20Twitter%20Experience.pdf

Scaling big data mining infrastructure: the twitter experience

The objective of our work is to detect hate speech in the Indonesian language. As far as we know, the research on this subject is still very rare. The only research we found has created a dataset for hate speech against religion, but the quality of this dataset is inadequate. Our research aimed to create a new dataset that covers hate speech in general, including hatred for religion, race, ethnicity, and gender. In addition, we also conducted a preliminary study using machine learning approach. Machine learning so far is the most frequently used approach in classifying text. We compared the performance of several features and machine learning algorithms for hate speech detection. Features that extracted were word n-gram with n=l and n=2, character n-gram with n=3 and n=4, and negative sentiment. The classification was performed using Naive Bayes, Support Vector Machine, Bayesian Logistic Regression, and Random Forest Decision Tree. An F-measure of 93.5% was achieved when using word n-gram feature with Random Forest Decision Tree algorithm. Results also show that word n-gram feature outperformed character n-gram.

Hate speech detection in the Indonesian language: A dataset and preliminary study

The increasing number of unsolicited e-mail messages (spam) reveals the need for the development of reliable anti-spam filters. The vast majority of content-based techniques rely on word-based repr...

Ioannis Houvardas

Papers

Words versus character n-grams for anti-spam filtering