Dialect variation

Relatively little research on dialect variation has been based on corpora of naturally occurring language. Instead, dialect variation has been studied based primarily on language elicited through questionnaires and interviews. Eliciting dialect data has several advantages, including allowing for dialectologists to select individual informants, control the communicative situation in which language is collected, elicit rare forms directly, and make high-quality audio recordings. Although far less common, a corpus-based approach to data collection also has several advantages, including allowing for dialectologists to collect large amounts of data from a large number of informants, observe dialect variation across a range of communicative situations, and analyze quantitative linguistic variation in large samples of natural language. Although both approaches allow for dialect variation to be observed, they provide different perspectives on language variation and change. The corpus- based approach to dialectology has therefore produced a number of new findings, many of which challenge traditional assumptions about the nature of dialect variation. Most important, this research has shown that dialect variation involves a wider range of linguistic variables and exists across a wider range of language varieties than has previously been assumed. The goal of this chapter is to introduce this emerging approach to dialectology. The first part of this chapter reviews the growing body of research that analyzes dialect variation in corpora, including research on variation across nations, regions, genders, ages, and classes, in both speech and writing, and from both a synchronic and diachronic perspective, with a focus on dialect variation in the English language. Although collections of language data elicited through interviews and questionnaires are now commonly referred to as corpora in sociolinguistics and dialectology (e.g. see Bauer 2002; Tagliamonte 2006; Kretzschmar et al. 2006; D'Arcy 2011), this review focuses on corpora of naturally occurring texts and discourse. The second part of this chapter presents the results of an analysis of variation in not contraction across region, gender, and time in a corpus of American English letters to the editor in order to exemplify a corpus-based approach to dialectology.

Exploring demographic information in social media for product recommendation

In many e-commerce Web sites, product recommendation is essential to improve user experience and boost sales. Most existing product recommender systems rely on historical transaction records or Web-site-browsing history of consumers in order to accurately predict online users’ preferences for product recommendation. As such, they are constrained by limited information available on specific e-commerce Web sites. With the prolific use of social media platforms, it now becomes possible to extract product demographics from online product reviews and social networks built from microblogs. Moreover, users’ public profiles available on social media often reveal their demographic attributes such as age, gender, and education. In this paper, we propose to leverage the demographic information of both products and users extracted from social media for product recommendation. In specific, we frame recommendation as a learning to rank problem which takes as input the features derived from both product and user demographics. An ensemble method based on the gradient-boosting regression trees is extended to make it suitable for our recommendation task. We have conducted extensive experiments to obtain both quantitative and qualitative evaluation results. Moreover, we have also conducted a user study to gauge the performance of our proposed recommender system in a real-world deployment. All the results show that our system is more effective in generating recommendation results better matching users’ preferences than the competitive baselines.

Analyzing lexical emergence in Modern American English online

This paper introduces a quantitative method for identifying newly emerging word forms in large time-stamped corpora of natural language and then describes an analysis of lexical emergence in American social media using this method based on a multi-billion word corpus of Tweets collected between October 2013 and November 2014. In total 29 emerging word forms, which represent various semantic classes, grammatical parts-of speech, and word formations processes, were identified through this analysis. These 29 forms are then examined from various perspectives in order to begin to better understand the process of lexical emergence.

Regional variation in written American English

The first study of its kind, Regional Variation in Written American English takes a corpus-based approach to map over a hundred grammatical alternation variables across the United States. A multivariate spatial analysis of these maps shows that grammatical alternation variables follow a relatively small number of common regional patterns in American English, which can be explained based on both linguistic and extra-linguistic factors. Based on this rigorous analysis of extensive data, Grieve identifies five primary modern American dialect regions, demonstrating that regional variation is far more pervasive and complex in natural language than is generally assumed. The wealth of maps and data and the groundbreaking implications of this volume make it essential reading for students and researchers in linguistics, English language, geography, computer science, sociology and communication studies.

Collaborative filtering and deep learning based recommendation system for cold start items

Recommender system is a specific type of intelligent systems, which exploits historical user ratings on items and/or auxiliary information to make recommendations on items to the users. It plays a critical role in a wide range of online shopping, e-commercial services and social networking applications. Collaborative filtering (CF) is the most popular approaches used for recommender systems, but it suffers from complete cold start (CCS) problem where no rating record are available and incomplete cold start (ICS) problem where only a small number of rating records are available for some new items or users in the system. In this paper, we propose two recommendation models to solve the CCS and ICS problems for new items, which are based on a framework of tightly coupled CF approach and deep learning neural network. A specific deep neural network SADE is used to extract the content features of the items. The state of the art CF model, timeSVD++, which models and utilizes temporal dynamics of user preferences and item features, is modified to take the content features into prediction of ratings for cold start items. Extensive experiments on a large Netflix rating dataset of movies are performed, which show that our proposed recommendation models largely outperform the baseline models for rating prediction of cold start items. The two proposed recommendation models are also evaluated and compared on ICS items, and a flexible scheme of model retraining and switching is proposed to deal with the transition of items from cold start to non-cold start status. The experiment results on Netflix movie recommendation show the tight coupling of CF approach and deep learning neural network is feasible and very effective for cold start item recommendation. The design is general and can be applied to many other recommender systems for online shopping and social networking applications. The solution of cold start item problem can largely improve user experience and trust of recommender systems, and effectively promote cold start items.

Collaborative filtering and deep learning based hybrid recommendation for cold start problem

Recommender systems (RS) are used by many social networking applications and online e-commercial services. Collaborative filtering (CF) is one of the most popular approaches used for RS. However traditional CF approach suffers from sparsity and cold start problems. In this paper, we propose a hybrid recommendation model to address the cold start problem, which explores the item content features learned from a deep learning neural network and applies them to the timeSVD++ CF model. Extensive experiments are run on a large Netflix rating dataset for movies. Experiment results show that the proposed hybrid recommendation model provides a good prediction for cold start items, and performs better than four existing recommendation models for rating of non-cold start items.