Twitter hashtags: Joint translation and clustering

The popularity of microblogging platforms, such as Twitter, ren-ders them valuable real-time information resources for tracking var-ious aspects of worldwide events, e.g., earthquakes, political elec-tions, etc. Such events are usually characterized in microblog posts via the use of hashtags (#). As microbloggers come from differ-ent backgrounds, and express themselves in different languages, we witness different “translations ” of hashtags which, however, are about the same event. Language-dependent variants of hashtags can possibly lead to issues in content-analysis. In this paper, we propose a method for translating hashtags, which builds on meth-ods from information retrieval. The method introduced is source and target language independent. Our method is desirable, either instead of, or complimentary, to the direct translation of the hash-tag for three reasons. First we return a list of hashtags on the same topic, which takes into account the plurality and variability of hashtags used by microbloggers for assigning posts to a topic. Second, our framework accounts for the problem that microblog-gers in different languages will refer to the same topic using dif-ferent tokens. Finally, our method does not require special pre-processing of hashtags, reducing barriers to real-world implemen-tation. We present proof-of-concept results for the given Spanish hashtag #33mineros