Search

Choosing a comprehensive and cost-effective way of articulating and annotating the sentiment of a text is not a trivial task, particularly when dealing with short texts, in which sentiment can be expressed through a wide variety of linguistic and rhetorical phenomena. This problem is especially conspicuous in resource-limited settings and languages, where design options are restricted either in terms of manpower and financial means required to produce appropriate sentiment analysis resources, or in terms of available language tools, or both. In this paper, we present a versatile approach to addressing this issue, based on multiple interpretations of sentiment labels that encode information regarding the polarity, subjectivity, and ambiguity of a text, as well as the presence of sarcasm or a mixture of sentiments. We demonstrate its use on Serbian, a resource-limited language, via the creation of a main sentiment analysis dataset focused on movie comments, and two smaller datasets belonging to the movie and book domains. In addition to measuring the quality of the annotation process, we propose a novel metric to validate its cost-effectiveness. Finally, the practicality of our approach is further validated by training, evaluating, and determining the optimal configurations of several different kinds of machine-learning models on a range of sentiment classification tasks using the produced dataset.

Neil Armstrong insisted that his quote upon landing on the moon was misheard, and that he had said one small step for a man, instead of one small step for man. What he said is unclear in part because function words like a can be reduced and spectrally indistinguishable from the preceding context. Therefore, their presence can be ambiguous, and they may disappear perceptually depending on the rate of surrounding speech. Two experiments are presented examining production and perception of reduced tokens of for and for a in spontaneous speech. Experiment 1 investigates the distributions of several acoustic features of for and for a. The results suggest that the distributions of for and for a overlap substantially, both in terms of temporal and spectral characteristics. Experiment 2 examines perception of these same tokens when the context speaking rate differs. The perceptibility of the function word a varies as a function of this context speaking rate. These results demonstrate that substantial ambiguity exists in the original quote from Armstrong, and that this ambiguity may be understood through context speaking rate.

Pictorial stimuli are commonly used by scientists to explore central processes; including memory, attention, and language. Pictures that have been collected and put into sets for these purposes often contain visual ambiguities that lead to name disagreement amongst subjects. In the present work, we propose new norms which reflect these sources of name disagreement, and we apply this method to two sets of pictures: the Snodgrass and Vanderwart (S&V) set and the Bank of Standardized Stimuli (BOSS). Naming responses of the presented pictures were classified within response categories based on whether they were correct, incorrect, or equivocal. To characterize the naming strategy where an alternative name was being used, responses were further divided into different sub-categories that reflected various sources of name disagreement. Naming strategies were also compared across the two sets of stimuli. Results showed that the pictures of the S&V set and the BOSS were more likely to elicit alternative specific and equivocal names, respectively. It was also found that the use of incorrect names was not significantly different across stimulus sets but that errors were more likely caused by visual ambiguity in the S&V set and by a misuse of names in the BOSS. Norms for name disagreement presented in this paper are useful for subsequent research for their categorization and elucidation of name disagreement that occurs when choosing visual stimuli from one or both stimulus sets. The sources of disagreement should be examined carefully as they help to provide an explanation of errors and inconsistencies of many concepts during picture naming tasks.

Visual lexical decision is a classical paradigm in psycholinguistics, and numerous studies have assessed the so-called "lexicality effect" (i.e., better performance with lexical than non-lexical stimuli). Far less is known about the dynamics of choice, because many studies measured overall reaction times, which are not informative about underlying processes. To unfold visual lexical decision in (over) time, we measured participants' hand movements toward one of two item alternatives by recording the streaming x,y coordinates of the computer mouse. Participants categorized four kinds of stimuli as "lexical" or "non-lexical:" high and low frequency words, pseudowords, and letter strings. Spatial attraction toward the opposite category was present for low frequency words and pseudowords. Increasing the ambiguity of the stimuli led to greater movement complexity and trajectory attraction to competitors, whereas no such effect was present for high frequency words and letter strings. Results fit well with dynamic models of perceptual decision-making, which describe the process as a competition between alternatives guided by the continuous accumulation of evidence. More broadly, our results point to a key role of statistical decision theory in studying linguistic processing in terms of dynamic and non-modular mechanisms.

While there has been a fair amount of research investigating children’s syntactic processing during spoken language comprehension, and a wealth of research examining adults’ syntactic processing during reading, as yet very little research has focused on syntactic processing during text reading in children. In two experiments, children and adults read sentences containing a temporary syntactic ambiguity while their eye movements were monitored. In Experiment 1, participants read sentences such as, ‘The boy poked the elephant with the long stick/trunk from outside the cage’ in which the attachment of a prepositional phrase was manipulated. In Experiment 2, participants read sentences such as, ‘I think I’ll wear the new skirt I bought tomorrow/yesterday. It’s really nice’ in which the attachment of an adverbial phrase was manipulated. Results showed that adults and children exhibited similar processing preferences, but that children were delayed relative to adults in their detection of initial syntactic misanalysis. It is concluded that children and adults have the same sentence-parsing mechanism in place, but that it operates with a slightly different time course. In addition, the data support the hypothesis that the visual processing system develops at a different rate than the linguistic processing system in children.