Article Preview
Top1. Introduction
Nowadays, the major part of the digital content is generated within public and enterprise techno-social systems like Facebook, Twitter, blogs, wiki systems, and other web-based collaborations and hosting tools, office suites, and project management tools, as well as proprietary databases. The notion of techno-social systems has been introduced in the paper by Maruev et al. (2015) and later developed in the book by Troussov and Maruev (2018). In these techno-social systems, individuals are connected to other individuals and to artefacts such as documents, datasets, analytic tools, and concepts.
Social media, such as Facebook, Instagram, and Twitter account for a specific important example of techno-social systems. Although the main points of the book by Troussov and Maruev (2018) hold true for social media, their case requires special consideration. There are two major reasons for this. First and foremost, texts language on the social media differs significantly from the “ordinary” one be it literary, business or technical language. Second, there are a number of new publications, which were not discussed in the above-mentioned works.
Overall, the paper is organized in the following manner.
The first section contains the general exposition on the issue of the nature of meaning in philosophy. From the point of view of the so-called ordinary language philosophy, meaningfulness of words in sentences is primarily determined by the ways in which they were put to use in the practical activity and the role they played in a broader context of the lifestyle. The contemporary lifestyle is inherent in social media with its virtual discourse which is determined not only by the words used but also by the relationships between the agents that generate them.
How far should one broaden the notion of the context in the Frege’s context principle? It is evident that any meaningful discussion on this issue should include considerations regarding the entire relevant context, which can be adequately taken into account. In other words, the context actually helps to understand the meaning of words, and it is computationally feasible to do so.
In this paper, a two-stage task of finding the proper context on social media is explored. It is obviously important to combine text analysis of the content with the structure of users’ network on social media. However, different groups of users might use the same term differently. Therefore, once the general properties of interconnections between words and social links are understood, these properties should be used to develop a technique for narrowing down the context immediately. A particular recent technique which allows finding groups of users connected by common interests and social links is observed. Such a group of interconnected users and the content they generate and discuss in this group could be considered as a context, probably much more useful than the context of the entire social network. It is evident that such a computation cannot produce a unique answer since the same user writing the same text could simultaneously participate in several contexts (for instance, as a computational linguist, and as a computer scientist). Once such technique is in place, it can be used in the following way. A proper context can be selected for a particular term in a particular text based on the set of computed contexts. Though the technique is already successfully applied, it is to be seen how it can be used for selecting the proper context.
The second section called “Texts in Social Media” is focused on linguistic aspects of text processing on social media. It begins with the analysis of the general contemporary approach to social networks analysis. Then, the linguistic problems of social networks texts research (including the ubiquitous use of colloquial style, everyday vocabulary, computer and network jargon, smileys and special punctuation, creolization of texts, communicative mimicry, word coinage) are described.