OAR@UM Collection:
/library/oar/handle/123456789/11950
2025-12-26T15:31:55ZFrom tweets to narratives : using tweets to generate news reports
/library/oar/handle/123456789/14744
Title: From tweets to narratives : using tweets to generate news reports
Abstract: Over the last decade or so, social media websites have begun to play an important role in
the dissemination of all types of news and information. One of the main attractions of using
social media is the ability to generate content, access information and potentially reach
large audiences. With user-generated content constantly being created and distributed
across social media platforms, the opportunities to harvest and analyse such data and
information have opened up new possibilities within a number of different fields of
research. Twitter, for instance, boasts three hundred and ten million monthly active users.
One could imagine that an intelligent system may be able to read through a set of tweets
and return the information and messages conveyed within the tweets in the form of a news
report. Due to a fascination with the field of natural language generation and a strong
interest in social media and sentiment analysis, the idea of generating a text which is able to
summarise the facts and opinions found in tweets seemed to offer a better alternative to
reading through a set of tweets individually.
This dissertation focuses on the design and implementation of an NLG system which is able
to identify a set of tweets using a particular query, collect such tweets, and generate an
output text. The text produced by the system takes the form of a news report narrative
where the most frequently mentioned facts within the tweets are incorporated within the
report generated. As part of the dissertation, a study was undertaken to investigate a
possible way of grouping Twitter topics according to their hashtags, to attempt to collect
similar tweets with different hashtags. The system was implemented using Python and Java,
with each tweet being dependency parsed to extract and define relations between words
and phrases. Two different approaches were used to convert the dependency parses of the
individual tweets into meaningful content to be used within the texts. Sentiment analysis
was also added to the project, with user sentiment across tweets reported within the
generated news report. The system returned some interesting output texts which were
used within a human-based evaluation to judge the fluency and content of the news reports. Although the texts generated were not of a very high standard, the evaluation
concluded that they were of a satisfactory level, with the best text produced according to
the evaluation achieving average scores of 5.71 and 5.64 (out of 10) for its fluency and
content respectively. The results obtained through the two different approaches used to
determine the content to generate are also analysed in detail, with one approach achieving
better overall results and potentially highlighting a way forward for such a system to be
used and developed further.
Description: M.SC.LANG.&COMPUTATION2016-01-01T00:00:00ZMaltese-speaking children in an unusual communicative situation
/library/oar/handle/123456789/13377
Title: Maltese-speaking children in an unusual communicative situation
Abstract: This qualitative study explores the interaction of six Maltese speaking children aged 4 to 6 with
an Italian speaker who does not usually use any English or Maltese. The purpose of this study
is to investigate what the children resort to when they need to communicate whilst interacting
with the Italian speaker. The study looks at both the verbal and non-verbal communication
with particular reference to gesture production. A comparison of the children’s utterances and
gesture productions is made and discussed. The findings reveal that the children prefer visual
gestures such as iconic, deictic and pantomimic over symbolic gestures. Facial cues such as
eye-gazing for verbal feedback were also investigated. Other findings revealed that children
used simple utterances in their interactions with the Italian speaker. Contrary to what might
have been hypothesised, the findings also revealed that the vast majority preferred Maltese in
the picture labelling task and English in the object labelling task. Despite these language
preferences in these two tasks, most of the children preferred Maltese over English throughout
the whole conversation. This reveals how Maltese still continues to dominate notwithstanding
Malta’s official bilingual status even where the children were aware that the Italian speaker
rarely used any Maltese or English. This study is a first step to try and provide insight into how
Maltese children produce gestures in diverse and rich linguistic contexts.
Description: B.A.(HONS)LINGUISTICS2016-01-01T00:00:00ZAdjective-noun compounds in Maltese : a semantic approach
/library/oar/handle/123456789/13376
Title: Adjective-noun compounds in Maltese : a semantic approach
Abstract: This dissertation sets out to investigate the semantic properties of Maltese A + N compounds. In this respect, it serves as a continuation of Fabri (2009), where a formal account of this group of expressions is put forth. Going through the general literature on compounding, the distinguishing characteristics of this category are isolated, and the rationale of a study that aims at establishing whether the meaning of these compounds is processed compositionally or idiomatically is presented. The empirical study that is then reported is based on a task where participants had to assess the acceptability of sentences containing the relevant compounds versus identical sentences containing only the compound’s adjectival head. The results of the study reveal that Maltese A + N compounds are most likely compositional and thus their meaning is derived from their constituent parts, especially from their adjectival head. Furthermore, the possibility of these compounds having an animacy restriction, as postulated by Fabri (2009) is also explored, which leads to somewhat mixed results. However, in an item by item analysis it turns out that there is some sort of animacy restriction. This however, needs to be researched further. All in all, this study can act as a further stepping stone in the investigation of this neglected area of the Maltese language.
Description: B.A.(HONS)LINGUISTICS2016-01-01T00:00:00ZA comparative study of pitch range in female bilingual Maltese and Maltese English speakers
/library/oar/handle/123456789/13375
Title: A comparative study of pitch range in female bilingual Maltese and Maltese English speakers
Abstract: This dissertation examines mean pitch and pitch range in Maltese and Maltese English female
bilinguals. Specifically, the pitch of bilingual speakers is measured and the pitch range is
calculated in order to figure out whether pitch varies across speakers with different language
dominance. It also seeks to establish whether pitch and pitch range are influenced by whether a
bilingual speaker is using Maltese or English). A secondary aim of the study was to determine
what kind of material is best suited to research on pitch range.
After a brief introduction to the Maltese bilingual context, a review of the relevant literature on
pitch is provided in order to identify both the phonetic properties of pitch as well as its
phonological correlates. These two factors build on one another and are crucial for the
identification of pitch range. An overview of studies on pitch range, including of different
methodologies used in such research was also carried out.
Mean pitch and pitch range in a population of fifteen female bilingual speakers, aged 18-27 was
examined through recordings of two types of data: read text data and sentence data. The speakers
were split into three groups having different language backgrounds and dominance (Maltese,
Maltese English and Gozitan dialect). These speakers were recorded whilst reading material in
both Maltese and English.
The results show that language dominance is a valid variable and that speakers’ mean pitch and
pitch range differs depending on their language dominance. Specifically, Gozitan dialect
dominant speakers have been found to have the lowest mean pitch as well as pitch range, in both
Maltese and English. In response to the secondary aim of this study, it was found that sentence
data containing different sentence types gives more explanatory power to the analysis.
Pitch range research is still very limited in Maltese and Maltese English and thus further studies
can be carried out on the topic, also building on the findings of this study.
Description: B.A.(HONS)LINGUISTICS2016-01-01T00:00:00Z